© 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. 114048
    Prev
    Next
    INDEX
    Explanations

    general population

    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
     brinde
    -1.62
    のご紹介
    -1.52
    Spéc
    -1.47
     aprendiz
    -1.45
    Partager
    -1.43
     encontraron
    -1.42
    さんです
    -1.39
     presentaron
    -1.38
    してくれた
    -1.38
     filós
    -1.38
    POSITIVE LOGITS
     system
    1.80
     estekak
    1.56
     environment
    1.56
     vicinity
    1.55
    那些
    1.48
     economy
    1.48
    🥉
    1.45
    或
    1.42
     вас
    1.41
    她
    1.41
    Activations Density 0.262%

    No Known Activations