© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1103
    Prev
    Next
    INDEX
    Explanations

    prison

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

    This neuron detects formal legal references and citations (e.g. court names, case numbers, sections, and related terminology).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⛱
    0.73
     diosa
    0.64
     epiph
    0.63
     গ্যাসের
    0.62
     WooCommerce
    0.61
     Seesaw
    0.61
    撐
    0.61
    🥞
    0.61
    🥂
    0.60
    🌂
    0.60
    POSITIVE LOGITS
     prison
    3.11
     inmate
    2.92
     incarcerated
    2.88
     prisons
    2.86
     prisoners
    2.84
     Prison
    2.83
     incarceration
    2.81
     prisoner
    2.77
    Prison
    2.77
    prison
    2.73
    Activations Density 0.770%

    No Known Activations