© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 24445
    Prev
    Next
    INDEX
    Explanations

    games in various languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    turbine
    0.42
    রোধ
    0.42
    output
    0.40
    쭌
    0.40
     Gewer
    0.40
    👢
    0.40
    သွယ်
    0.39
     محصولات
    0.39
     PROTE
    0.38
    潞
    0.38
    POSITIVE LOGITS
     game
    1.47
     게임
    1.45
     games
    1.42
    游戏的
    1.37
    ゲーム
    1.35
    Game
    1.33
     Game
    1.28
     गेम
    1.28
    游戏
    1.26
    เกม
    1.23
    Activations Density 0.231%

    No Known Activations