© 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. 38417
    Prev
    Next
    INDEX
    Explanations

    contexts for study or work

    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
    ونی
    -1.39
    襌
    -1.26
     faciliter
    -1.24
     Gewer
    -1.20
    ㎡
    -1.19
    廰
    -1.17
    pageNo
    -1.17
    “-
    -1.16
     spécialement
    -1.16
    》，
    -1.15
    POSITIVE LOGITS
     in
    2.05
     while
    1.80
     although
    1.70
     despite
    1.53
    although
    1.34
     have
    1.30
    Although
    1.27
     through
    1.25
    教師
    1.24
    ใน
    1.20
    Activations Density 0.396%

    No Known Activations