© 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. 114063
    Prev
    Next
    INDEX
    Explanations

    people and foreign "for"s

    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
    AL
    -2.58
    in
    -2.53
    即便是
    -2.30
    In
    -2.28
    with
    -2.27
    .
    -2.23
     данного
    -2.19
     красивая
    -2.19
     newest
    -2.16
     Augenblick
    -2.13
    POSITIVE LOGITS
     برای
    2.97
     für
    2.67
     voor
    2.53
     για
    2.52
     для
    2.45
     they
    2.45
    犛
    2.45
    蹌
    2.23
    儿的
    2.19
     untuk
    2.17
    Activations Density 0.030%

    No Known Activations