© 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-RES-262K
    7. 2409
    Prev
    Next
    INDEX
    Explanations

    salt and pepper

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

    markers of highly structured or technical text—acronyms/abbreviations, tagging/format labels, numerals and dates, units, and code- or punctuation-heavy tokens, rather than ordinary prose.

    oai_token-act-pair · gpt-5
    Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     that
    0.29
     hẳn
    0.27
     (
    0.26
     что
    0.25
     άλλ
    0.25
     Emeritus
    0.24
     their
    0.24
     বিকল্প
    0.24
     Wellington
    0.24
     Communications
    0.24
    POSITIVE LOGITS
    ہار
    0.32
     など
    0.31
     definisi
    0.31
     ។
    0.31
     پانچ
    0.31
     イベント
    0.30
    ៧
    0.30
     letzte
    0.30
     제거
    0.30
     verfol
    0.30
    Activations Density 0.733%

    No Known Activations