© 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. 10-GEMMASCOPE-RES-131K
    7. 80760
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by names or titles

    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
     acheter
    -1.73
     abiye
    -1.63
    鰱
    -1.63
     panas
    -1.63
    against
    -1.61
    obtain
    -1.55
     שלהם
    -1.53
    齜
    -1.53
    "",
    -1.53
     -"
    -1.53
    POSITIVE LOGITS
     for
    2.13
     to
    1.75
     by
    1.70
     or
    1.70
     on
    1.69
     with
    1.68
     in
    1.66
     επίσης
    1.63
     also
    1.63
     ebenfalls
    1.61
    Activations Density 0.020%

    No Known Activations