© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13116
    Prev
    Next
    INDEX
    Explanations

    ten games

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

    code, data, or numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-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
    ار
    0.86
    ون
    0.86
    ar
    0.83
    u
    0.83
    các
    0.80
    िंग
    0.79
    ین
    0.79
    an
    0.78
    es
    0.78
    их
    0.77
    POSITIVE LOGITS
    重要
    0.74
    S
    0.73
    0
    0.72
    ﺭ
    0.72
     mari
    0.71
     stvar
    0.70
    Dalam
    0.69
    İ
    0.68
    මත්
    0.68
    GI
    0.66
    Activations Density 0.884%

    No Known Activations