© 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. 29900
    Prev
    Next
    INDEX
    Explanations

    acts and legislation

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

    The neuron fires on formal legal‐document metadata and headings—uppercase terms (e.g. “OF,” “THE,” “JUSTICES”), legislative bodies, section and citation numbers, and other header‐style tokens.

    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
    šana
    -0.87
     under
    -0.79
    Deus
    -0.77
    ⊓
    -0.74
     csrf
    -0.73
    Elems
    -0.72
     અને
    -0.72
    หน่อย
    -0.72
    これからも
    -0.69
    shafen
    -0.68
    POSITIVE LOGITS
     Acts
    1.47
     laws
    1.41
     Laws
    1.28
    Laws
    1.23
     Session
    1.20
    Acts
    1.18
     Act
    1.13
     acts
    1.11
     legislation
    1.06
    Session
    1.04
    Activations Density 0.032%

    No Known Activations