© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 6913
    Prev
    Next
    INDEX
    Explanations

    exclamations, admissions, and errors

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

    The neuron fires on isolated, title‐style or header‐style tokens—single words or interjections (often capitalized or punctuation‐marked) that serve as section titles, error messages, or standalone labels.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     eviden
    -2.19
    臙
    -2.17
    🥰
    -2.06
    🙆
    -2.06
    Transk
    -2.05
    ：[
    -2.03
    ﮯ
    -2.00
     obt
    -2.00
     fufficient
    -1.99
    💪
    -1.98
    POSITIVE LOGITS
    “
    2.55
    {
    2.42
    なども
    2.14
    ’
    2.09
     debemos
    1.99
     
    1.91
    とその
    1.90
    2
    1.90
     Demonstrate
    1.89
    1
    1.89
    Activations Density 0.001%

    No Known Activations