© 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. 127698
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on markup and code‐block delimiters (e.g. HTML/XML tags, code fence backticks, and similar container markers).

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

    document headings and code markers

    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
    ranno
    -1.04
    💃
    -1.00
    izia
    -0.99
    nelse
    -0.98
     inútil
    -0.97
    ≦
    -0.97
    ꯠ
    -0.96
     to
    -0.96
    opot
    -0.95
    Ѕ
    -0.95
    POSITIVE LOGITS
    凝土
    0.96
    这些
    0.95
    Raúl
    0.94
    Analy
    0.93
     Kampagne
    0.92
     možná
    0.91
     Unterscheidung
    0.91
     pesso
    0.90
     costruire
    0.90
    GLFW
    0.89
    Activations Density 0.000%

    No Known Activations