© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 13544
    Prev
    Next
    INDEX
    Explanations

    cloud configuration

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
     schm
    0.63
    ницы
    0.54
    ించ
    0.53
     proportional
    0.50
     AV
    0.50
     __
    0.50
     sten
    0.50
    bik
    0.50
    fifths
    0.49
     Fremont
    0.48
    POSITIVE LOGITS
    随
    0.63
    游戏
    0.62
    溶液
    0.61
     рейти
    0.61
    角色
    0.59
    的游戏
    0.59
     Role
    0.58
    资讯
    0.58
    遊戲
    0.57
    ランク
    0.57
    Activations Density 0.000%

    No Known Activations