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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7902
    Prev
    Next
    INDEX
    Explanations

    program code identifiers

    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
     Jimenez
    -0.82
     phấn
    -0.77
     influence
    -0.75
     since
    -0.73
     jerawat
    -0.73
    aip
    -0.73
    MD
    -0.71
     Interpre
    -0.70
    ipeline
    -0.69
     dintre
    -0.69
    POSITIVE LOGITS
     godine
    0.77
    供应商
    0.76
    ceans
    0.76
    さんへ
    0.75
    콥
    0.74
    xmax
    0.73
    )~
    0.73
    ToBe
    0.73
    Figures
    0.73
    prach
    0.73
    Activations Density 0.003%

    No Known Activations