© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65041
    Prev
    Next
    INDEX
    Explanations

    bench trial, jury trial, hearing

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

    The neuron detects references to legal procedural contexts—mentions of trials, courts, and rules of procedure.

    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
    atern
    -0.74
    zanne
    -0.73
     actividades
    -0.68
    花の
    -0.68
     setName
    -0.65
    hdl
    -0.65
     Zain
    -0.64
    RAV
    -0.64
    ントランス
    -0.63
    allee
    -0.63
    POSITIVE LOGITS
     jury
    2.73
     Jury
    1.95
     trial
    1.86
    jury
    1.77
    Jury
    1.73
    Trial
    1.47
     Trial
    1.39
    trial
    1.37
     trials
    1.34
     bench
    1.31
    Activations Density 0.087%

    No Known Activations