© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72147
    Prev
    Next
    INDEX
    Explanations

    peak or height of

    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
    Negative Logits
    ↵↵
    -1.77
    vaded
    -1.77
     according
    -1.63
    ਨ
    -1.59
    xla
    -1.59
    袮
    -1.59
     ocasi
    -1.59
    erializer
    -1.50
     faintly
    -1.48
     verwijzen
    -1.48
    POSITIVE LOGITS
    s
    1.91
    色々な
    1.59
     our
    1.57
    潆
    1.52
    h
    1.52
     klarer
    1.52
    ma
    1.50
    푣
    1.50
     gestire
    1.48
    껏
    1.48
    Activations Density 0.011%

    No Known Activations