© 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. 58713
    Prev
    Next
    INDEX
    Explanations

    anyone can do

    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
    <bos>
    -1.52
     других
    -1.50
     
    -1.46
     другими
    -1.39
     inoxidable
    -1.38
    ↵↵↵
    -1.38
     другие
    -1.35
     سایر
    -1.34
     nuov
    -1.32
    튿
    -1.31
    POSITIVE LOGITS
     but
    1.36
    創意
    1.31
    arrivo
    1.30
    Menurutnya
    1.30
     ціка
    1.23
     because
    1.23
    しなければ
    1.20
    がありますが
    1.20
    していますが
    1.20
     should
    1.19
    Activations Density 0.033%

    No Known Activations