© 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
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9091
    Prev
    Next
    INDEX
    Explanations

    feature engineering

    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_31_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
    g
    0.68
    Có
    0.66
    Came
    0.65
    ملك
    0.63
    i
    0.63
     factors
    0.62
     Ná
    0.62
    ก
    0.62
    方案
    0.61
    ផ្នែក
    0.61
    POSITIVE LOGITS
     prominently
    1.21
     feature
    0.82
     संपन्न
    0.76
    feature
    0.74
     plow
    0.72
     Feature
    0.71
     grafting
    0.70
     FEATURE
    0.70
     extraction
    0.69
    tte
    0.69
    Activations Density 0.075%

    No Known Activations