© 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. 83715
    Prev
    Next
    INDEX
    Explanations

    ethnic or national groups

    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
    bekistan
    -0.98
     vrijdag
    -0.95
     countries
    -0.86
    menistan
    -0.82
     zaterdag
    -0.80
    تاريخ
    -0.78
     افغانستان
    -0.75
    VISA
    -0.74
     Namibia
    -0.73
    Countries
    -0.72
    POSITIVE LOGITS
     Hindu
    1.37
    Muslim
    1.36
     Muslim
    1.36
     Jewish
    1.35
     Greek
    1.32
     Sinh
    1.30
     Arab
    1.27
     евре
    1.21
    Jewish
    1.18
     Bengali
    1.18
    Activations Density 0.080%

    No Known Activations