© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 40228
    Prev
    Next
    INDEX
    Explanations

    Islam, Abrahamic religions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    س
    2.56
    ل
    2.55
    ט
    1.89
    ПО
    1.82
    ى
    1.81
    ע
    1.80
    쌉
    1.77
    Ин
    1.76
    РО
    1.75
    ג
    1.73
    POSITIVE LOGITS
    aw
    1.91
    うちに
    1.89
    ization
    1.85
    atically
    1.85
    ming
    1.84
    mm
    1.83
     reale
    1.77
    ara
    1.75
    mington
    1.72
    hotmail
    1.72
    Activations Density 0.004%

    No Known Activations