© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81526
    Prev
    Next
    INDEX
    Explanations

    paragraph symbol and numbering

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

    The neuron strongly responds to standalone numbers and numeric identifiers (e.g. page numbers, docket or paragraph symbols, and case citation numbers) in a legal-document header.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    válasz
    -0.88
     Landwirtschaft
    -0.85
    适用于
    -0.84
    utre
    -0.78
    lero
    -0.77
    similiano
    -0.77
     encantan
    -0.73
     if
    -0.72
     mini
    -0.72
     peculiar
    -0.72
    POSITIVE LOGITS
     paragraphs
    1.39
    paragraph
    1.34
     paragraph
    1.31
    paragraphs
    1.20
    Paragraph
    1.15
     Paragraph
    1.09
    para
    1.04
    Para
    1.04
     para
    0.94
    paras
    0.94
    Activations Density 0.015%

    No Known Activations