© 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. 30156
    Prev
    Next
    INDEX
    Explanations

    section numbers

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

    The neuron strongly activates on legal or regulatory section and statute citations (e.g., “Section 304,” “§ 1112,” “SOX”).

    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
     Gazetteer
    -0.89
    ждений
    -0.76
    람
    -0.74
     Hezbollah
    -0.74
    Árbitro
    -0.73
     Gaz
    -0.72
    련
    -0.71
     Amts
    -0.69
    按照
    -0.68
    ieuse
    -0.68
    POSITIVE LOGITS
     Section
    1.44
    Section
    1.44
     section
    1.38
     Sections
    1.09
    section
    1.02
    SECTION
    1.02
     sections
    0.99
     SECTION
    0.95
    Sections
    0.92
     сек
    0.92
    Activations Density 0.030%

    No Known Activations