© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11386
    Prev
    Next
    INDEX
    Explanations

    gesture recognition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    鳢
    -3.00
    鋱
    -2.83
    灃
    -2.73
     شیپور
    -2.58
    ﮕ
    -2.50
    ⼠
    -2.50
    ୮
    -2.44
    펨
    -2.36
     پشتی
    -2.33
    鯪
    -2.33
    POSITIVE LOGITS
    ’
    3.02
     
    2.58
     Where
    2.42
    "
    2.13
    他现在
    1.99
     ”
    1.96
    '
    1.96
    的
    1.94
    ”(
    1.94
     Там
    1.92
    Activations Density 0.003%

    No Known Activations