© 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. 72348
    Prev
    Next
    INDEX
    Explanations

    html document start

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

    The neuron is activated by HTML structural markup—especially the “<!DOCTYPE html>” declaration and angle-bracket tokens (“<” and “>”) that mark the start of an HTML document.

    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
     but
    -1.84
     Then
    -1.83
     then
    -1.76
     them
    -1.65
    one
    -1.44
     who
    -1.39
     than
    -1.38
    なのかな
    -1.38
     dann
    -1.34
     Untersuchungen
    -1.34
    POSITIVE LOGITS
    țiile
    1.41
    旰
    1.40
    iligten
    1.38
    ihnachts
    1.34
     eléctricos
    1.34
    　　《
    1.34
    妁
    1.33
     dekoratif
    1.32
     decorativos
    1.30
     ヶ
    1.30
    Activations Density 0.031%

    No Known Activations