© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106278
    Prev
    Next
    INDEX
    Explanations

    countries and regions

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on references to countries, regions, or geographic groupings in a statistical or demographic context.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    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
    Negative Logits
     countries
    -1.35
     país
    -1.21
     country
    -1.20
    ประเทศ
    -1.11
     países
    -1.09
    COUNTRY
    -1.06
     страны
    -1.02
    Countries
    -0.94
     Countries
    -0.94
     کشور
    -0.93
    POSITIVE LOGITS
     UN
    0.85
    has
    0.80
    Ð
    0.79
    cay
    0.77
    cart
    0.76
     Европы
    0.75
     League
    0.75
    GroupBox
    0.74
     Eurovision
    0.74
     lainnya
    0.73
    Activations Density 0.047%

    No Known Activations