© 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. 116583
    Prev
    Next
    INDEX
    Explanations

    geopolitical states and zones

    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
     richtigen
    -0.92
    lings
    -0.91
     régional
    -0.86
    باء
    -0.81
     sindaco
    -0.79
     liefert
    -0.77
    getTime
    -0.77
     richtige
    -0.77
     sugerencias
    -0.77
     metrics
    -0.77
    POSITIVE LOGITS
     geo
    1.10
     Geo
    0.97
     geopolitical
    0.92
     zone
    0.91
     states
    0.90
     Zone
    0.87
    geo
    0.85
    GEO
    0.85
     GEO
    0.84
     sen
    0.82
    Activations Density 0.008%

    No Known Activations