© 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. 10-GEMMASCOPE-RES-131K
    7. 20434
    Prev
    Next
    INDEX
    Explanations

    judges and court panels

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

    This neuron detects the capitalized judge names and initials in the case‐caption or “Present” line of a court opinion.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     interessantes
    -1.49
     Vereinbarung
    -1.33
    mender
    -1.29
     Actualmente
    -1.27
     crochê
    -1.27
     anúncios
    -1.23
    MÁS
    -1.22
     kyt
    -1.21
    彳
    -1.19
     gemeinsamen
    -1.17
    POSITIVE LOGITS
     there
    1.82
     only
    1.35
     who
    1.27
     gives
    1.26
     they
    1.20
     that
    1.16
     after
    1.16
    ímite
    1.15
     gave
    1.15
     this
    1.15
    Activations Density 0.141%

    No Known Activations