© 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. 83763
    Prev
    Next
    INDEX
    Explanations

    human rights lawyer or artist names

    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
     to
    -2.30
     Sometimes
    -1.64
     or
    -1.59
     otras
    -1.55
    ;
    -1.50
     продукта
    -1.49
     dilaksanakan
    -1.48
     другим
    -1.48
    та
    -1.46
     werfen
    -1.45
    POSITIVE LOGITS
    diseases
    1.68
     obfer
    1.59
     milieux
    1.57
     dieß
    1.53
     here
    1.48
    毉
    1.46
     fapt
    1.46
     poffe
    1.45
    Arbe
    1.37
    begins
    1.36
    Activations Density 0.001%

    No Known Activations