Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8713
    Prev
    Next
    INDEX
    Explanations

    code constructs and programming keywords

    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
    invokeLater
    -0.82
     parishes
    -0.80
    Ę
    -0.78
    
    -0.77
     Dioxide
    -0.77
     ә
    -0.77
    Empresa
    -0.75
    Ӏ
    -0.73
    Oxy
    -0.73
     PREPAR
    -0.73
    POSITIVE LOGITS
     reject
    0.81
     erhielt
    0.77
    ヨ
    0.77
    puede
    0.75
    フラン
    0.74
     clip
    0.74
    当時は
    0.74
    caron
    0.74
    formance
    0.73
    後で
    0.73
    Activations Density 0.011%

    No Known Activations