© 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. 7924
    Prev
    Next
    INDEX
    Explanations

    use with hooks

    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
     when
    -2.36
     if
    -1.77
    皲
    -1.63
     to
    -1.60
    戗
    -1.54
    釭
    -1.51
     ‘‘
    -1.50
     vieler
    -1.48
     after
    -1.47
     با
    -1.44
    POSITIVE LOGITS
    龊
    1.99
    ésil
    1.72
    ORDER
    1.72
    饜
    1.63
    鷽
    1.63
    今日は
    1.57
    Seperti
    1.56
     الإلكتر
    1.55
    Karena
    1.52
    Setiap
    1.52
    Activations Density 0.003%

    No Known Activations