© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 16104
    Prev
    Next
    INDEX
    Explanations

    completed and enjoyable

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

    game choices and strategy

    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_262k_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
    ó
    0.54
     übers
    0.53
    yta
    0.51
    حت
    0.50
     ì
    0.50
    ew
    0.50
    פל
    0.50
    hews
    0.50
    daa
    0.49
    encent
    0.49
    POSITIVE LOGITS
    وها
    0.46
    धित
    0.44
    绊
    0.43
     Proficiency
    0.43
     keterampilan
    0.42
    皑
    0.42
    र
    0.40
    細胞
    0.40
    getDouble
    0.40
    TP
    0.39
    Activations Density 0.000%

    No Known Activations