© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 31437
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
     obtient
    0.80
     sorprend
    0.79
     avaient
    0.77
    夎
    0.76
     utilizz
    0.75
     ショルダーバッグ
    0.74
    지
    0.74
    直播
    0.74
     diperoleh
    0.74
     pertanto
    0.74
    POSITIVE LOGITS
    ны
    0.88
    AN
    0.82
    ный
    0.82
    ANTS
    0.80
    ын
    0.79
    Аль
    0.78
    おく
    0.78
    हे
    0.75
    ных
    0.75
     sogen
    0.75
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.