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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40551
    Prev
    Next
    INDEX
    Explanations

    class or interface inheritance

    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_10/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
     was
    -2.39
    ’
    -2.05
    </h1>
    -2.00
    _
    -1.73
    e
    -1.69
     be
    -1.62
    ↵↵↵
    -1.60
     by
    -1.59
     has
    -1.53
     also
    -1.52
    POSITIVE LOGITS
     inverno
    1.95
    ჻
    1.90
     sorgfäl
    1.82
     Mientras
    1.81
    🛇
    1.78
    ℣
    1.77
     investimento
    1.70
     beträ
    1.69
    
    1.67
     Además
    1.66
    Activations Density 0.005%

    No Known Activations