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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8256
    Prev
    Next
    INDEX
    Explanations

    two-letter abbreviations

    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
    con
    -0.88
    agaimana
    -0.80
    手間
    -0.78
    呼ぶ
    -0.77
     each
    -0.77
    后
    -0.76
     finally
    -0.75
     con
    -0.75
     initially
    -0.75
    locke
    -0.74
    POSITIVE LOGITS
    ཫ
    1.03
    woners
    0.97
    ソニー
    0.94
    Stateless
    0.93
    centric
    0.93
    graphers
    0.92
    ʕ
    0.92
     drôle
    0.91
    här
    0.90
    getE
    0.90
    Activations Density 0.037%

    No Known Activations