© 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. 22-GEMMASCOPE-RES-131K
    7. 13550
    Prev
    Next
    INDEX
    Explanations

    Plaintiff versus Defendant

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

    The neuron detects legal party role labels (e.g. “Plaintiff,” “Defendant,” “Employer,” “Carrier,” “Employee,” etc.) in case captions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     Is
    -1.30
     You
    -1.17
    u
    -1.14
    R
    -1.11
    T
    -1.11
     Ta
    -1.10
    b
    -1.09
    M
    -1.09
    U
    -1.09
     en
    -1.08
    POSITIVE LOGITS
     répon
    1.47
     vlož
    1.23
    Reak
    1.22
     fré
    1.18
     Tó
    1.17
     biela
    1.17
    Konto
    1.16
     réve
    1.16
    Aç
    1.14
     kontinu
    1.13
    Activations Density 0.140%

    No Known Activations