© 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. 118787
    Prev
    Next
    INDEX
    Explanations

    public/private declarations

    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
    zał
    -0.88
    Boolean
    -0.83
    ų
    -0.81
     ilustracji
    -0.80
    เสื้อ
    -0.78
     السعودية
    -0.77
    unft
    -0.77
     months
    -0.77
    なんだ
    -0.77
     Strawberry
    -0.77
    POSITIVE LOGITS
    static
    1.19
     final
    1.16
    final
    1.09
    /**
    0.99
     static
    0.92
    thumbsup
    0.91
    protected
    0.90
    stech
    0.90
     finally
    0.90
     finalmente
    0.89
    Activations Density 0.014%

    No Known Activations