© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9091
    Prev
    Next
    INDEX
    Explanations

    feature engineering

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on occurrences of the word “feature” (in any form or hyphenated compound), marking mentions of features.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ارتی
    0.70
    حر
    0.69
    ه
    0.67
    ก
    0.67
    倾向
    0.67
    για
    0.66
    യ
    0.66
    ملك
    0.65
    सा
    0.64
    к
    0.64
    POSITIVE LOGITS
     prominently
    1.63
     feature
    0.81
     длина
    0.78
    featured
    0.75
     FEATURE
    0.75
     heavily
    0.73
     뽑
    0.71
     suasana
    0.71
     prominent
    0.70
     Feature
    0.69
    Activations Density 0.062%

    No Known Activations