© 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. 53800
    Prev
    Next
    INDEX
    Explanations

    bills and legislation

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

    The neuron fires on structured document headers and metadata—things like legislative or court session identifiers, bill or docket numbers, section titles and other all-caps heading lines.

    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
     continual
    -0.84
    stery
    -0.78
     svå
    -0.77
     Bakan
    -0.76
     bakgrund
    -0.71
    ابط
    -0.71
    Doctrine
    -0.71
     jsonData
    -0.71
    мый
    -0.71
     onix
    -0.71
    POSITIVE LOGITS
     bill
    1.38
     senate
    1.13
     предлага
    1.09
    ]-\
    1.02
     Senate
    1.02
     Bill
    0.98
     Senators
    0.94
     BILL
    0.92
     bills
    0.90
    bill
    0.89
    Activations Density 0.039%

    No Known Activations