© 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. 80875
    Prev
    Next
    INDEX
    Explanations

    South Carolina cities and places

    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
     Maharashtra
    -0.76
    Purdue
    -0.75
    isticas
    -0.75
    澳
    -0.73
     >&
    -0.72
     tokio
    -0.72
     Minneapolis
    -0.71
    ParseTree
    -0.69
     teş
    -0.69
     Weimar
    -0.69
    POSITIVE LOGITS
     Charleston
    1.92
     SC
    1.88
    Charleston
    1.69
     Clemson
    1.66
     Carolina
    1.63
     South
    1.59
    Carolina
    1.59
    South
    1.44
     Aiken
    1.43
     Bamberg
    1.43
    Activations Density 0.082%

    No Known Activations