© 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. 80918
    Prev
    Next
    INDEX
    Explanations

    countries and nationalities

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

    The neuron strongly responds to country- and nationality-related terms (including demonyms, language names, and other proper nouns for nations).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     Nigeria
    -1.80
     Nigerian
    -1.73
    Nigeria
    -1.57
     niger
    -1.33
     NIGERIA
    -1.29
    Nigerian
    -1.25
     Nigerians
    -1.10
     Lagos
    -0.95
    niger
    -0.93
     Abuja
    -0.83
    POSITIVE LOGITS
     United
    1.03
     UNITED
    0.93
     countries
    0.89
     racially
    0.88
     американ
    0.82
    United
    0.81
     países
    0.78
     Britons
    0.78
     American
    0.76
     Americans
    0.76
    Activations Density 0.014%

    No Known Activations