© 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. 71827
    Prev
    Next
    INDEX
    Explanations

    finding things

    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
     более
    -1.52
     by
    -1.39
     lieber
    -1.34
    ofed
    -1.32
    five
    -1.24
     $
    -1.23
    ʻ
    -1.22
     schonmal
    -1.20
    ès
    -1.17
    ¹
    -1.17
    POSITIVE LOGITS
     would
    1.49
     such
    1.34
     synerg
    1.24
     success
    1.23
    raga
    1.19
     viata
    1.19
    やめ
    1.12
    vensko
    1.12
    viä
    1.12
     why
    1.12
    Activations Density 0.272%

    No Known Activations