© 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-262K
    7. 35658
    Prev
    Next
    INDEX
    Explanations

    game related concepts

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

    playing a game

    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
    ৭
    1.02
    に
    0.86
    에
    0.82
    in
    0.79
    嵬
    0.79
    oč
    0.78
    werken
    0.78
    Y
    0.78
    டி
    0.77
    lių
    0.77
    POSITIVE LOGITS
    ند
    0.97
     and
    0.96
     games
    0.95
     игры
    0.92
     on
    0.90
    ص
    0.77
     oyun
    0.75
    ни
    0.75
    نا
    0.75
    న్
    0.74
    Activations Density 0.051%

    No Known Activations