© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 80837
    Prev
    Next
    INDEX
    Explanations

    regions and countries

    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
    Not in Any Lists

    No Comments

    Negative Logits
    notFound
    -0.89
     kathol
    -0.89
    ndim
    -0.88
     alleged
    -0.87
    Når
    -0.87
     Gemeinder
    -0.85
     contemporary
    -0.84
     Shortcuts
    -0.82
    andal
    -0.82
     croce
    -0.81
    POSITIVE LOGITS
     region
    2.30
     regions
    2.16
    region
    2.05
     Region
    1.95
    Region
    1.92
    regions
    1.88
     regional
    1.77
     REGION
    1.73
    regional
    1.69
     Regions
    1.68
    Activations Density 0.082%

    No Known Activations