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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11406
    Prev
    Next
    INDEX
    Explanations

    source code form licensing

    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
     with
    -2.27
     at
    -1.95
     it
    -1.85
     without
    -1.77
     despite
    -1.77
     on
    -1.75
     even
    -1.73
     has
    -1.73
     comes
    -1.66
     using
    -1.63
    POSITIVE LOGITS
     predominantly
    1.63
     REALLY
    1.63
     VERY
    1.59
     mediocre
    1.50
     goofy
    1.49
    ⪧
    1.48
    primarily
    1.48
     áng
    1.48
     principalement
    1.48
     AMAZING
    1.48
    Activations Density 0.000%

    No Known Activations