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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 128826
    Prev
    Next
    INDEX
    Explanations

    religious and ethnic groups

    np_acts-logits-general · gemini-2.5-flash-lite

    mosque ethnicity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    邰
    0.52
    ลอด
    0.48
    inguished
    0.47
     веще
    0.47
     бота
    0.47
    😧
    0.46
     Toxicol
    0.45
    膑
    0.45
    Aircraft
    0.45
    暏
    0.45
    POSITIVE LOGITS
     ۽
    0.59
     Kurds
    0.55
     និង
    0.53
     ਅਤੇ
    0.52
     Sunni
    0.50
     mosques
    0.49
     و
    0.48
     आणि
    0.48
     અને
    0.48
     Muslim
    0.48
    Activations Density 0.006%

    No Known Activations