© 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
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1142
    Prev
    Next
    INDEX
    Explanations

    HTML element tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    ع
    0.82
    ب
    0.80
    ح
    0.77
    ف
    0.77
    حص
    0.66
    м
    0.66
    حی
    0.65
    ል
    0.64
    وط
    0.62
    cie
    0.61
    POSITIVE LOGITS
     altri
    0.67
     altre
    0.63
    ">
    0.63
     outros
    0.63
    //{
    0.63
     другими
    0.60
     innymi
    0.58
     diğer
    0.57
     अन्य
    0.57
    >${
    0.56
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.