© 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. 3754
    Prev
    Next
    INDEX
    Explanations

    made or built

    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
     Два
    0.69
    它
    0.66
    ઍ
    0.64
    ए
    0.64
    А
    0.64
     Doppio
    0.61
     beamed
    0.59
    不断的
    0.59
    О
    0.59
     Assists
    0.59
    POSITIVE LOGITS
    pts
    0.68
     anew
    0.66
     trên
    0.65
     μέσω
    0.64
    FACTORY
    0.64
    с
    0.63
     by
    0.62
     обязанности
    0.60
     στο
    0.59
     vía
    0.59
    Activations Density 0.014%

    No Known Activations