© 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. 44631
    Prev
    Next
    INDEX
    Explanations

    lists of names or authors

    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
     arriver
    -1.83
    orious
    -1.80
    hopefully
    -1.77
    mittag
    -1.76
     çantası
    -1.73
     acheter
    -1.72
     varier
    -1.70
     ومت
    -1.65
     visiter
    -1.64
    
    -1.63
    POSITIVE LOGITS
     now
    2.22
     also
    2.08
     not
    1.95
     more
    1.94
     ebenfalls
    1.89
     for
    1.88
     because
    1.84
     in
    1.80
     to
    1.78
     about
    1.75
    Activations Density 0.008%

    No Known Activations