© 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. 34-GEMMASCOPE-RES-131K
    7. 94247
    Prev
    Next
    INDEX
    Explanations

    code block endings

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    𝕒
    -0.91
    ✨
    -0.77
     karo
    -0.76
     jari
    -0.75
     Robinson
    -0.74
     Jesu
    -0.74
    Dealer
    -0.73
    лось
    -0.73
     directo
    -0.72
     garçon
    -0.72
    POSITIVE LOGITS
     stop
    1.34
    stop
    1.19
    endsection
    1.11
     end
    1.05
    END
    0.99
     Stop
    0.98
     stops
    0.95
     ends
    0.93
    Stop
    0.91
     stopping
    0.90
    Activations Density 0.003%

    No Known Activations