© 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-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30546
    Prev
    Next
    INDEX
    Explanations

    religious concepts and practices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bel
    0.38
     ску
    0.37
     벨
    0.36
    reset
    0.36
     кою
    0.36
    Sco
    0.36
    uyentes
    0.35
     Belmont
    0.35
     vegetal
    0.35
    irar
    0.35
    POSITIVE LOGITS
     impro
    0.41
    custList
    0.38
     adjud
    0.38
     schne
    0.37
    minin
    0.37
    譁
    0.37
     adjudication
    0.36
     कट्टर
    0.36
     minDist
    0.36
    whitelist
    0.35
    Activations Density 0.018%

    No Known Activations