© 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. 22-GEMMASCOPE-RES-131K
    7. 71021
    Prev
    Next
    INDEX
    Explanations

    code structures and data representations

    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_22/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
     privil
    -1.09
     meras
    -0.93
     ancien
    -0.93
     gardent
    -0.93
     mû
    -0.93
     quitt
    -0.93
     continuer
    -0.92
     celles
    -0.92
    Sociology
    -0.91
    Ahhhh
    -0.90
    POSITIVE LOGITS
     as
    0.94
    komsten
    0.88
    他說
    0.87
     should
    0.86
     if
    0.86
     that
    0.86
     loosely
    0.84
     क्यों
    0.82
     überzeugen
    0.82
    áss
    0.82
    Activations Density 0.037%

    No Known Activations