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. 8240
    Prev
    Next
    INDEX
    Explanations

    document provider

    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
     oito
    -0.74
    UED
    -0.73
     decidiu
    -0.72
    menn
    -0.72
     кар
    -0.72
     добавил
    -0.71
     prochains
    -0.71
    ループ
    -0.71
     Hưng
    -0.70
    rigs
    -0.69
    POSITIVE LOGITS
     document
    1.16
    document
    1.10
     Document
    0.99
     documents
    0.94
     Dokument
    0.93
    ocument
    0.93
     edited
    0.91
     buffer
    0.88
     документ
    0.88
     lines
    0.88
    Activations Density 0.045%

    No Known Activations