© 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. 10-GEMMASCOPE-RES-131K
    7. 120109
    Prev
    Next
    INDEX
    Explanations

    US, Canada, States, border

    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_10/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
     Unterschiede
    -1.00
     osób
    -0.98
     muito
    -0.97
    也
    -0.96
     vorliegenden
    -0.95
     specificity
    -0.94
     camera
    -0.91
     аудио
    -0.91
    嘎
    -0.91
    εσ
    -0.90
    POSITIVE LOGITS
    첫
    1.03
     Viernes
    1.02
     pirm
    1.01
    位的
    1.00
    toarele
    1.00
    
    0.91
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.91
     sosis
    0.91
     kapsul
    0.90
    namely
    0.90
    Activations Density 0.112%

    No Known Activations