© 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. 50329
    Prev
    Next
    INDEX
    Explanations

    Muslim world organizations

    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
     натура
    -0.74
    唱歌
    -0.72
     toxic
    -0.71
     cumpri
    -0.70
    alline
    -0.69
    pato
    -0.68
    тивен
    -0.67
    τα
    -0.66
     яи
    -0.66
    stripe
    -0.66
    POSITIVE LOGITS
     Muslim
    1.04
     Islamic
    1.03
     Organisation
    1.02
    Muslim
    0.96
    Organisation
    0.94
     Organization
    0.92
    Islamic
    0.90
     League
    0.88
    League
    0.88
    ρεί
    0.88
    Activations Density 0.017%

    No Known Activations