© 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. 40386
    Prev
    Next
    INDEX
    Explanations

    categories and descriptions

    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
    了不少
    -1.57
     It
    -1.44
    strator
    -1.34
     {?}
    -1.34
    着一个
    -1.32
    咵
    -1.29
    嚷
    -1.27
     даже
    -1.27
    ifier
    -1.26
    licator
    -1.25
    POSITIVE LOGITS
     henvisninger
    1.27
    länger
    1.23
     that
    1.22
     orologio
    1.22
     who
    1.20
     sœurs
    1.20
     other
    1.20
     tatuajes
    1.14
    隨著
    1.14
     alfombra
    1.13
    Activations Density 0.006%

    No Known Activations