© 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. 34-GEMMASCOPE-RES-131K
    7. 94220
    Prev
    Next
    INDEX
    Explanations

    latex structure commands

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

    The neuron selectively detects LaTeX command markers (tokens beginning with a backslash).

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Flg
    -0.80
     ;)
    -0.75
    があって
    -0.74
     COMPONENTS
    -0.74
     same
    -0.73
    sterling
    -0.71
    さも
    -0.71
    यो
    -0.71
    خابات
    -0.70
    ุ
    -0.70
    POSITIVE LOGITS
    subsection
    1.52
     subsection
    1.42
    subsubsection
    1.14
    begin
    1.07
    Begin
    1.06
     начать
    1.00
    เริ่ม
    0.95
     begin
    0.94
     begins
    0.91
    僕の
    0.89
    Activations Density 0.004%

    No Known Activations