© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 5810
    Prev
    Next
    INDEX
    Explanations

    The goal is to find a pattern that explains what the neuron detects or predicts.The explanation should be concise (3-20 words), a phrase, or a pattern, not a sentence.**MAX_ACTIVATING_TOKENS**:- hair- Hair- hair- hair- Hair- water- hair- light- water- sandThe token "hair" appears most frequently (5 out of 10). "Water" appears twice. "Light" and "sand" appear once. This suggests a primary focus on physical descriptions, potentially related to appearance or environment.**TOKENS_AFTER_MAX_ACTIVATING_TOKEN**:- colour (after hair)- :** (after Hair)- styling (after hair)- : (after hair)- :** (after Hair)- temperature (after water)- less (after hair)- , (after water)- conservation (after water)- , (after sand)This list provides context."hair colour" and "hair styling" are directly mentioned."water temperature

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    1.05
    ب
    0.97
    ov
    0.95
    up
    0.94
     ouv
    0.89
    जी
    0.87
    પ
    0.85
    ่
    0.85
    SD
    0.80
     kefir
    0.79
    POSITIVE LOGITS
    ान
    0.95
    ução
    0.91
    uslararası
    0.86
    arası
    0.85
    Ⲓ
    0.85
    ェ
    0.84
     utilización
    0.83
     Такие
    0.81
    iunea
    0.81
    ieth
    0.80
    Activations Density 0.131%

    No Known Activations