© 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. 22-GEMMASCOPE-RES-131K
    7. 12334
    Prev
    Next
    INDEX
    Explanations

    Jewish people, ancestry, and history

    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_22/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
    U
    -2.33
    .”
    -2.23
    ↵
    -2.09
     eyebrow
    -2.08
     effortlessly
    -2.02
    很重要
    -2.02
     analysing
    -2.00
    i
    -1.98
    );
    -1.96
     que
    -1.95
    POSITIVE LOGITS
    ly
    2.22
     ontdek
    2.05
    鹮
    1.94
     начинают
    1.93
    Ꮿ
    1.88
    
    1.88
     sportowe
    1.85
     sposa
    1.84
     снимки
    1.82
     powinien
    1.79
    Activations Density 0.007%

    No Known Activations