© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 6221
    Prev
    Next
    INDEX
    Explanations

    especially, special, origin, relation

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

    specialized or nonstandard tokens—especially acronyms, numerals/ranges, hyphenated forms, and capitalized or diacritic-laden foreign proper nouns.

    oai_token-act-pair · gpt-5Triggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    squirrel
    0.16
    n
    0.16
    aaa
    0.16
    ंडे
    0.16
    kron
    0.16
    鏉
    0.16
    ao
    0.15
     proverbial
    0.15
    a
    0.15
    aide
    0.15
    POSITIVE LOGITS
     特に
    0.20
     prostu
    0.19
    を中心
    0.19
     nových
    0.19
     REGIUNI
    0.18
     područ
    0.18
     originalmente
    0.18
     odnosu
    0.18
    病的
    0.17
     特別
    0.17
    Activations Density 3.991%

    No Known Activations