© 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. 98280
    Prev
    Next
    INDEX
    Explanations

    utility classes and static methods

    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
     investors
    -0.85
     вось
    -0.84
     complejo
    -0.83
     Nhân
    -0.78
     Anzeigen
    -0.77
     бое
    -0.77
    ailles
    -0.76
    stle
    -0.76
    たと
    -0.75
    nition
    -0.75
    POSITIVE LOGITS
    工具类
    1.87
     utility
    1.84
     Utility
    1.68
    Utility
    1.62
     utils
    1.48
     utilities
    1.45
     UTIL
    1.45
     Utils
    1.43
     util
    1.37
    Utils
    1.34
    Activations Density 0.075%

    No Known Activations