© 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. 47276
    Prev
    Next
    INDEX
    Explanations

    North America and Canada

    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
     without
    -0.91
     statewide
    -0.88
    NgModule
    -0.84
     remove
    -0.82
     one
    -0.82
     removed
    -0.78
     go
    -0.78
     nationally
    -0.76
     removing
    -0.75
     Maharashtra
    -0.75
    POSITIVE LOGITS
     Canada
    2.22
     North
    2.02
    Canada
    1.91
     Canadian
    1.91
     continent
    1.80
    North
    1.78
    Canadian
    1.69
     Canadá
    1.63
     CANADA
    1.62
     Canad
    1.60
    Activations Density 0.062%

    No Known Activations