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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 12-GEMMASCOPE-2-RES-16K
    7. 394
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_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
    很多
    0.57
    見た
    0.56
     Поскольку
    0.56
    い
    0.56
    Á
    0.56
    
    0.54
    гава
    0.54
    /////////////
    0.54
    У
    0.54
    Traditionally
    0.53
    POSITIVE LOGITS
    ar
    0.76
    as
    0.72
    ہ
    0.71
    am
    0.70
    ز
    0.70
    ang
    0.69
    us
    0.68
    ah
    0.67
    ار
    0.66
    ور
    0.65
    Activations Density 13.787%

    No Known Activations