© 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. 67986
    Prev
    Next
    INDEX
    Explanations

    attribution of cause

    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
     information
    -2.05
     or
    -1.95
     what
    -1.95
     new
    -1.77
     if
    -1.66
     one
    -1.64
     strangely
    -1.64
     all
    -1.63
    中止
    -1.55
     in
    -1.53
    POSITIVE LOGITS
     semelh
    1.86
    屨
    1.79
    mainly
    1.76
    ↵
    1.75
    扨
    1.73
    紲
    1.73
     déplo
    1.73
     then
    1.73
    烀
    1.72
    primarily
    1.71
    Activations Density 0.034%

    No Known Activations