© 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. 114222
    Prev
    Next
    INDEX
    Explanations

    and providing details

    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
    TION
    -1.42
    拶
    -1.39
    badan
    -1.36
    MOND
    -1.34
    APOLIS
    -1.28
    ULATION
    -1.28
    OLOGICAL
    -1.27
    Ꮴ
    -1.25
    sheng
    -1.24
     miljø
    -1.23
    POSITIVE LOGITS
     when
    1.61
     through
    1.46
     to
    1.43
     just
    1.42
     because
    1.41
     can
    1.40
     by
    1.39
    ？』
    1.38
     like
    1.37
     while
    1.37
    Activations Density 0.105%

    No Known Activations