© 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. 7758
    Prev
    Next
    INDEX
    Explanations

    instances of off

    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
    er
    -2.39
    wiście
    -2.36
    on
    -2.31
     in
    -2.30
    ar
    -2.30
     There
    -2.17
    re
    -2.16
    i
    -2.13
    mit
    -2.11
    at
    -2.08
    POSITIVE LOGITS
    ية
    2.64
    gridy
    2.53
    StoryboardSegue
    2.52
    лении
    2.50
    럿
    2.48
    能在
    2.41
     กับ
    2.23
    ⽌
    2.23
    щита
    2.23
    ྂ
    2.20
    Activations Density 0.011%

    No Known Activations