© 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. 67679
    Prev
    Next
    INDEX
    Explanations

    award winner

    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
    翃
    -1.70
    骉
    -1.67
    鴆
    -1.57
     них
    -1.53
    撳
    -1.52
    ffers
    -1.48
     mauva
    -1.48
    咈
    -1.38
    帏
    -1.37
    茈
    -1.36
    POSITIVE LOGITS
     on
    1.77
     his
    1.55
     for
    1.46
    多かった
    1.27
     through
    1.27
     two
    1.27
     without
    1.27
     благодаря
    1.27
     no
    1.25
     during
    1.24
    Activations Density 0.093%

    No Known Activations