© 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. 45479
    Prev
    Next
    INDEX
    Explanations

    automatic actions

    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
    Flashcards
    -1.38
    LLE
    -1.34
    実際に
    -1.30
     hvis
    -1.27
    ’，
    -1.23
     kemudian
    -1.20
    菝
    -1.20
    Hashes
    -1.15
    COLOG
    -1.15
     dalamnya
    -1.15
    POSITIVE LOGITS
     automatically
    2.02
     automatic
    1.89
     of
    1.80
    自动
    1.78
    auto
    1.75
    automatic
    1.75
     自动
    1.61
     Automatically
    1.59
     Automatic
    1.59
     автоматически
    1.56
    Activations Density 0.114%

    No Known Activations