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. 8076
    Prev
    Next
    INDEX
    Explanations

    names, code, and lyrics

    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
    解决方案
    -1.00
     cryptocurrency
    -0.97
     congregation
    -0.96
     disappointments
    -0.95
     procedimientos
    -0.95
     electromagnetic
    -0.95
    NSMutableArray
    -0.94
    companyname
    -0.93
     antidepressants
    -0.93
     Congregational
    -0.93
    POSITIVE LOGITS
    JMenu
    1.00
    ferrer
    0.94
     Editora
    0.93
    モダン
    0.91
     Pá
    0.88
    SnackBar
    0.87
    ViewSet
    0.87
    TryParse
    0.87
     efficacy
    0.87
     oratory
    0.86
    Activations Density 0.060%

    No Known Activations