© 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. 38586
    Prev
    Next
    INDEX
    Explanations

    support 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
     will
    -2.31
     It
    -2.22
     meticulously
    -2.09
     sleek
    -2.00
     more
    -1.97
     what
    -1.93
     give
    -1.88
     cleverly
    -1.88
     gives
    -1.88
     supremely
    -1.86
    POSITIVE LOGITS
     niedersachsen
    2.20
    usions
    2.02
     campagnes
    2.00
     間取り
    1.96
    說
    1.95
    鲧
    1.95
     GOtt
    1.90
    鉏
    1.88
     frança
    1.88
    sed
    1.85
    Activations Density 0.009%

    No Known Activations