© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15617
    Prev
    Next
    INDEX
    Explanations

    relative or normalized values

    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
    Negative Logits
     bustling
    -1.19
     mismas
    -1.17
     canopy
    -1.16
    ↵↵
    -1.15
     viviendas
    -1.14
     then
    -1.13
    Today
    -1.10
     лимон
    -1.09
    Both
    -1.09
    wski
    -1.09
    POSITIVE LOGITS
    asje
    1.23
    RELATIVE
    1.19
    vård
    1.19
     trimestre
    1.16
     stoff
    1.16
     like
    1.16
    ⡑
    1.16
    utveck
    1.15
     Relative
    1.14
    när
    1.13
    Activations Density 0.043%

    No Known Activations