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. 8028
    Prev
    Next
    INDEX
    Explanations

    laws and official documents

    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
    iestety
    -0.77
     Tamanho
    -0.74
    Diseño
    -0.74
    collana
    -0.73
    يارات
    -0.70
    Projeto
    -0.69
     Roberts
    -0.69
    泯
    -0.68
     Untersuchungen
    -0.68
    etzal
    -0.67
    POSITIVE LOGITS
    gette
    0.76
    Shapes
    0.75
     логоти
    0.75
    ESTR
    0.75
     alternativ
    0.73
    ByExample
    0.73
     Pradesh
    0.72
     about
    0.71
    ERP
    0.71
    EXP
    0.71
    Activations Density 0.007%

    No Known Activations