© 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. 83754
    Prev
    Next
    INDEX
    Explanations

    adjective noun

    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
     to
    -2.06
     in
    -1.73
     if
    -1.33
    eronau
    -1.27
     users
    -1.18
    ONDER
    -1.15
     have
    -1.14
     sides
    -1.12
    が付
    -1.10
    -1.10
    POSITIVE LOGITS
     уже
    1.30
     که
    1.30
     pieles
    1.27
     fordern
    1.23
    ógica
    1.17
     souligné
    1.17
     escote
    1.16
    émoc
    1.16
    スペイン
    1.16
    μά
    1.14
    Activations Density 0.127%

    No Known Activations