© 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. 58983
    Prev
    Next
    INDEX
    Explanations

    sports and locations

    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
     in
    -3.11
     for
    -2.61
     after
    -2.22
     from
    -2.00
     with
    -1.98
     before
    -1.87
     or
    -1.77
     that
    -1.73
     within
    -1.66
     which
    -1.65
    POSITIVE LOGITS
    atien
    1.62
     congrès
    1.53
    FFIX
    1.42
    γη
    1.40
    lossen
    1.40
    และ
    1.38
     Aula
    1.37
     konstru
    1.35
    <bos>
    1.35
    omla
    1.34
    Activations Density 0.066%

    No Known Activations