© 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. 129324
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and punctuation

    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
     komfor
    -1.63
     Scritto
    -1.57
    ítico
    -1.56
     sokak
    -1.43
     bunun
    -1.42
     ='
    -1.42
     profili
    -1.40
     сезон
    -1.39
     zaten
    -1.37
    ㅁ
    -1.37
    POSITIVE LOGITS
     and
    2.17
     your
    2.00
     will
    1.91
     always
    1.78
     has
    1.76
     as
    1.73
     by
    1.65
     in
    1.61
    嬉しいです
    1.52
     anklicken
    1.50
    Activations Density 0.306%

    No Known Activations