© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76270
    Prev
    Next
    INDEX
    Explanations

    application configuration paths

    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
     согла
    -0.77
    htaccess
    -0.76
     inici
    -0.72
    tesi
    -0.71
    ㌀
    -0.70
    厥
    -0.70
    Tembelea
    -0.69
    ABCDEF
    -0.69
     sưu
    -0.68
    Nbr
    -0.68
    POSITIVE LOGITS
     Sonata
    0.94
    Cache
    0.82
    Bundle
    0.79
    sf
    0.78
     Acme
    0.77
    ResourceBundle
    0.76
    SON
    0.75
    Legacy
    0.75
     Application
    0.74
     App
    0.74
    Activations Density 0.053%

    No Known Activations