© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 73862
    Prev
    Next
    INDEX
    Explanations

    attorney's fees and awards

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

    This neuron responds to numeric tokens—especially legal docket numbers, section citations, dates, and monetary figures—in court‐document text.

    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
     frenos
    -0.74
    pgm
    -0.73
     외
    -0.71
     Nog
    -0.69
     leth
    -0.68
    gain
    -0.68
    Speed
    -0.68
     Buffet
    -0.67
    bra
    -0.67
    alou
    -0.67
    POSITIVE LOGITS
     award
    1.52
     awarding
    1.49
     awards
    1.37
     awarded
    1.35
     fees
    1.24
     fee
    1.21
     Awards
    1.16
     Award
    1.16
     attorneys
    1.10
     Awarded
    1.07
    Activations Density 0.024%

    No Known Activations