© 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. 12015
    Prev
    Next
    INDEX
    Explanations

    Indian and US place names

    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
     Adelaide
    -0.86
     Cheltenham
    -0.83
     Pune
    -0.81
     UW
    -0.79
    quill
    -0.77
     Worcester
    -0.77
     uda
    -0.76
    Adelaide
    -0.75
    redis
    -0.75
     Fang
    -0.75
    POSITIVE LOGITS
     Bihar
    1.91
     Patna
    1.69
    Indiana
    1.20
     Evansville
    1.19
     Indiana
    1.17
     Louisville
    1.13
     Indianapolis
    1.09
    Indianapolis
    0.99
    Louisville
    0.97
    Laf
    0.94
    Activations Density 0.012%

    No Known Activations