© 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. 11190
    Prev
    Next
    INDEX
    Explanations

    tort, Tort, torture

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

    The neuron detects mentions of “tort” and related legal‐liability terms in contract or liability disclaimers.

    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
    ILER
    0.59
    ним
    0.59
    Supply
    0.58
    SOC
    0.55
    ราบ
    0.54
    석
    0.54
    फाइनल
    0.52
    थो
    0.52
    бла
    0.52
    rind
    0.52
    POSITIVE LOGITS
     produisent
    0.65
     tort
    0.63
     produire
    0.59
     Chandigarh
    0.58
     Augsburg
    0.57
    espół
    0.57
    tort
    0.57
    梧
    0.57
     Auburn
    0.56
     Wheaton
    0.56
    Activations Density 0.019%

    No Known Activations