© 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. 109884
    Prev
    Next
    INDEX
    Explanations

    multiculturalism and integration

    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
    榷
    -0.80
    AEL
    -0.78
    ضب
    -0.73
     colaborar
    -0.73
    ⇌
    -0.73
    เภ
    -0.71
    catus
    -0.71
    Bly
    -0.70
    cová
    -0.70
     cholera
    -0.69
    POSITIVE LOGITS
     multicultural
    1.54
     Multicultural
    1.44
     immigrant
    1.34
     integration
    1.27
     ethnic
    1.25
    ethnic
    1.20
    Integration
    1.18
     Integration
    1.13
    Mul
    1.13
    integration
    1.12
    Activations Density 0.021%

    No Known Activations