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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78766
    Prev
    Next
    INDEX
    Explanations

    OMB burden collection PRA

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

    The neuron activates on numeric sequences and legal/administrative identifiers (e.g., docket numbers, dates, and reference codes).

    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
    resentação
    -0.79
     profes
    -0.75
    elux
    -0.75
    µ
    -0.75
     kah
    -0.73
    唧
    -0.71
     bakal
    -0.71
    /%
    -0.70
    ورا
    -0.70
     гро
    -0.69
    POSITIVE LOGITS
     OMB
    1.66
    burden
    1.64
     burden
    1.62
     Burden
    1.47
    OMB
    1.40
     collection
    1.15
     burdens
    1.08
     PRA
    1.06
     collections
    1.02
    PRA
    0.99
    Activations Density 0.044%

    No Known Activations