© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63493
    Prev
    Next
    INDEX
    Explanations

    of America

    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
    Alexand
    -0.75
    edy
    -0.73
    捎
    -0.72
    ينه
    -0.71
     procedure
    -0.68
     :-(
    -0.65
     Algerian
    -0.65
     table
    -0.65
    いわゆる
    -0.65
    animation
    -0.64
    POSITIVE LOGITS
     America
    5.50
    America
    4.50
     america
    4.03
     AMERICA
    3.63
    america
    3.58
     Амери
    3.47
     América
    2.98
     Amerika
    2.63
    Amérique
    2.52
     آمریکا
    2.34
    Activations Density 0.079%

    No Known Activations