© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8606
    Prev
    Next
    INDEX
    Explanations

    just [number]

    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
     ENTIRE
    -1.70
     WHOLE
    -1.70
    峮
    -1.70
    tryck
    -1.62
     EVEN
    -1.61
     และ
    -1.61
     ljus
    -1.56
     liknande
    -1.54
     dansk
    -1.53
     huset
    -1.52
    POSITIVE LOGITS
     for
    2.19
     in
    2.08
     their
    1.70
     using
    1.68
     with
    1.66
     used
    1.59
     remove
    1.58
    (
    1.58
     from
    1.57
     before
    1.55
    Activations Density 0.019%

    No Known Activations