© 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. 14541
    Prev
    Next
    INDEX
    Explanations

    food and place names

    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
     as
    -1.62
     if
    -1.48
     about
    -1.41
    :
    -1.30
     these
    -1.27
     then
    -1.25
     because
    -1.23
     here
    -1.20
     a
    -1.16
     regarding
    -1.13
    POSITIVE LOGITS
    umbria
    1.34
     их
    1.24
    ukkah
    1.20
    estimable
    1.13
     более
    1.13
    否认
    1.10
    γράφ
    1.06
    ほら
    1.06
    ≧
    1.05
     that
    1.04
    Activations Density 0.134%

    No Known Activations