© 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. 109849
    Prev
    Next
    INDEX
    Explanations

    firearms and gun parts

    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
     Relig
    -0.75
     FRES
    -0.71
     défense
    -0.70
    Continua
    -0.69
     SONY
    -0.69
     exciter
    -0.68
     Haem
    -0.68
     Planetary
    -0.66
     LABOR
    -0.66
     AppBar
    -0.66
    POSITIVE LOGITS
     stock
    2.08
     stocks
    1.98
    stock
    1.91
     butt
    1.85
    stocks
    1.80
     Stock
    1.76
    Stock
    1.66
     Stocks
    1.65
    Stocks
    1.62
     STOCK
    1.59
    Activations Density 0.013%

    No Known Activations