© 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. 37996
    Prev
    Next
    INDEX
    Explanations

    Latter-day Saints and Utah

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

    LDS faith-based addiction programs

    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
     voj
    0.43
    掛
    0.41
    ویز
    0.40
    ^*\
    0.40
    長
    0.40
    นิ
    0.40
    告知
    0.39
     tox
    0.39
     niss
    0.39
     $*$-
    0.39
    POSITIVE LOGITS
     BYU
    1.23
     Mormon
    1.16
     LDS
    1.16
    Utah
    1.06
     Utah
    1.01
     Nephi
    1.01
     Latter
    1.00
     Brigham
    0.93
     Morm
    0.91
     Provo
    0.85
    Activations Density 0.083%

    No Known Activations