© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 88645
    Prev
    Next
    INDEX
    Explanations

    Jewish holidays

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

    Orthodoxy rabbis

    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
     Islamist
    0.64
     islamic
    0.64
     hijab
    0.63
     muslim
    0.62
     مسلمان
    0.61
     Muslim
    0.61
    🕌
    0.61
     islam
    0.60
     salwar
    0.59
     mosque
    0.58
    POSITIVE LOGITS
     greatness
    0.52
     repro
    0.49
     Louisiana
    0.48
     רבי
    0.47
     Vaughn
    0.47
     unbelievably
    0.47
     ד
    0.47
     Mississippi
    0.46
     Willie
    0.45
     reprim
    0.44
    Activations Density 0.053%

    No Known Activations