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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110438
    Prev
    Next
    INDEX
    Explanations

    nationalities or ethnicities

    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
     الدولي
    -0.94
     Rhodesia
    -0.89
     fraudul
    -0.88
     televisiva
    -0.85
     Россию
    -0.85
    微妙
    -0.85
    schen
    -0.85
    Élet
    -0.84
    bieron
    -0.84
    ómico
    -0.82
    POSITIVE LOGITS
     Germans
    3.03
     Americans
    3.00
     Russians
    2.94
     Italians
    2.67
     Europeans
    2.44
     Australians
    2.44
     Greeks
    2.41
     Koreans
    2.38
     Canadians
    2.33
     Israelis
    2.20
    Activations Density 0.052%

    No Known Activations