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. 8190
    Prev
    Next
    INDEX
    Explanations

    .127.0.0.1 connection

    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
     genotype
    -0.77
    zados
    -0.75
     LaSalle
    -0.72
    ález
    -0.70
     Cartoon
    -0.68
     Shen
    -0.68
     Toner
    -0.68
    ří
    -0.67
     dallo
    -0.66
     stipulated
    -0.65
    POSITIVE LOGITS
    Architect
    0.77
     controller
    0.72
    service
    0.71
     Architect
    0.70
     service
    0.68
     złot
    0.68
    牛奶
    0.67
    glBindBuffer
    0.67
    тері
    0.66
    eter
    0.64
    Activations Density 0.112%

    No Known Activations