© 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. 49592
    Prev
    Next
    INDEX
    Explanations

    attorney general

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

    This neuron detects formal legal entity names and titles (e.g. state names, “Attorney General,” and other uppercase proper nouns) in court-heading 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
    lorious
    -0.76
    gyro
    -0.76
     accueil
    -0.73
     Evaluación
    -0.73
    \":\"
    -0.73
    긴
    -0.72
     chers
    -0.71
     facturas
    -0.70
    éton
    -0.70
    mistak
    -0.70
    POSITIVE LOGITS
     Attorney
    2.55
    Attorney
    2.00
     AG
    1.93
     attorney
    1.60
    AG
    1.46
     Attorneys
    1.44
     Atty
    1.28
     ATTORNEY
    1.27
     attorneys
    1.26
     Consumer
    1.25
    Activations Density 0.159%

    No Known Activations