© 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. 34-GEMMASCOPE-RES-131K
    7. 109795
    Prev
    Next
    INDEX
    Explanations

    China, Chinese, growth, anniversary

    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_34/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
    ͢
    -0.85
    lblNewLabel
    -0.78
    альных
    -0.77
     knew
    -0.75
    Źródło
    -0.74
    cowboy
    -0.73
     разо
    -0.72
     almost
    -0.71
     chuť
    -0.71
     Almost
    -0.70
    POSITIVE LOGITS
    stamos
    0.91
    versaire
    0.88
    鴉
    0.83
    alleri
    0.81
     Marxist
    0.78
     Hough
    0.77
    лях
    0.77
    ains
    0.76
     Hedge
    0.75
     DATA
    0.75
    Activations Density 0.007%

    No Known Activations