© 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. 23795
    Prev
    Next
    INDEX
    Explanations

    american south and culture

    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
    bukkit
    -0.98
    COUVER
    -0.85
    Winnipeg
    -0.84
     Winnipeg
    -0.84
     célula
    -0.82
    VELAND
    -0.81
     Norwalk
    -0.81
     Honolulu
    -0.81
     bölüm
    -0.81
     Mumbai
    -0.81
    POSITIVE LOGITS
     Southern
    2.48
    Southern
    2.31
     southern
    2.17
     Alabama
    2.09
     Mississippi
    1.99
    southern
    1.93
    Alabama
    1.83
     Tennessee
    1.80
     SOUTHERN
    1.73
     Louisiana
    1.66
    Activations Density 0.103%

    No Known Activations