© 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. 59711
    Prev
    Next
    INDEX
    Explanations

    co-creation and collaboration

    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
     to
    -1.91
     of
    -1.85
     
    -1.72
     they
    -1.68
     leur
    -1.66
    They
    -1.63
     .
    -1.60
     It
    -1.52
    必定
    -1.48
    5
    -1.48
    POSITIVE LOGITS
    
    1.65
    笮
    1.55
    캉
    1.52
    ◘
    1.50
    战斗力
    1.49
     with
    1.44
    戕
    1.43
     voyez
    1.41
    Наталья
    1.40
    関連リンク
    1.40
    Activations Density 0.010%

    No Known Activations