© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67703
    Prev
    Next
    INDEX
    Explanations

    years and dates

    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
     in
    -2.77
     not
    -2.13
     to
    -2.05
     ‘
    -2.02
    ↵↵
    -1.93
    to
    -1.90
    -1.88
    这个
    -1.88
     for
    -1.84
    ,’
    -1.80
    POSITIVE LOGITS
    
    2.02
    .''
    1.88
     ་
    1.84
    ción
    1.80
     ebbe
    1.78
     congrès
    1.77
    湉
    1.74
    czna
    1.73
    OPSIS
    1.73
     agricole
    1.70
    Activations Density 0.088%

    No Known Activations