© 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. 32628
    Prev
    Next
    INDEX
    Explanations

    questions and forum help

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

    The neuron strongly activates on markup syntax tokens (e.g. HTML tags like “<p>” or LaTeX commands such as “sum_{”), i.e. bits of embedded formatting code.

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     to
    -1.10
    そして
    -1.05
    Даже
    -1.01
     povezave
    -1.01
     zdjęć
    -0.99
    onymes
    -0.99
    curité
    -0.98
    见状
    -0.97
    只见
    -0.97
     ją
    -0.97
    POSITIVE LOGITS
     verlangt
    1.16
    事です
    1.11
    感じが
    1.07
    マジで
    1.03
    様な
    1.02
     dringend
    1.01
    たびに
    1.01
    ところに
    0.95
    </strong>
    0.94
    imens
    0.93
    Activations Density 0.000%

    No Known Activations