© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 57570
    Prev
    Next
    INDEX
    Explanations

    ligaments, ligament, Hulu, riparian, pw, Carlisle

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

    words related to technical computer science terms and body parts, particularly focusing on anatomical structures.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron flags isolated jargon-style tokens—single-word technical identifiers or specialized terms (e.g. variable or function names, anatomical terms, proper nouns).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hinblick
    -3.22
     Then
    -2.50
     —
    -2.38
    [
    -2.30
     Gegensatz
    -2.23
     realmente
    -2.20
    $
    -2.19
    er
    -2.13
    .
    -2.11
     Heilige
    -2.09
    POSITIVE LOGITS
    ⬮
    2.83
    我还是
    2.81
    鱨
    2.45
    <bos>
    2.33
     parachoque
    2.28
    鄠
    2.27
    吓得
    2.27
    最高の
    2.17
    厯
    2.17
     processi
    2.16
    Activations Density 0.002%

    No Known Activations