© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 11655
    Prev
    Next
    INDEX
    Explanations

    legal restrictions

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

    The main thing this neuron does is detect mentions of laws, statutes, regulations, or legal requirements—often where they’re cited or numbered.

    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_24_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
    STARTED
    0.80
    colormap
    0.77
     Kursk
    0.77
     Фер
    0.74
    тились
    0.74
    OX
    0.73
     由
    0.72
     Кан
    0.72
     решению
    0.72
    Ｙ
    0.72
    POSITIVE LOGITS
     laws
    1.23
     enactment
    1.20
     enacted
    1.20
     statutes
    1.15
    laws
    1.13
     regulations
    1.11
     enact
    1.10
    law
    1.05
     statute
    1.05
    法规
    1.03
    Activations Density 0.089%

    No Known Activations