© 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. 22-GEMMASCOPE-RES-131K
    7. 127743
    Prev
    Next
    INDEX
    Explanations

    The neuron is detecting closing tags or end‐of‐element markers in HTML/XML/JSX code (i.e. “</…” or “/>”).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    HTML structure and elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    chaise
    -1.20
    mousse
    -1.20
    tative
    -1.15
    solicited
    -1.11
    راهن
    -1.08
     and
    -1.08
    madison
    -1.06
    madonna
    -1.04
     Popis
    -1.01
     StatelessWidget
    -1.00
    POSITIVE LOGITS
    詢問
    1.11
     ایش
    1.09
    h
    1.05
    le
    1.03
    诙
    0.98
     umbro
    0.97
     only
    0.96
    慫
    0.94
    ev
    0.93
    ār
    0.93
    Activations Density 0.008%

    No Known Activations