© 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. 31-GEMMASCOPE-2-RES-16K
    7. 2632
    Prev
    Next
    INDEX
    Explanations

    regulation and protection

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

    The neuron fires strongly on numeric identifiers—years, report numbers, document codes, and other digit‐based references.

    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
    男友
    0.77
    calcular
    0.65
    حصل
    0.63
    欧美
    0.62
    botao
    0.61
    Ꮜ
    0.61
     বাবার
    0.60
    tuvo
    0.60
    撂
    0.60
     Европы
    0.60
    POSITIVE LOGITS
     Protection
    0.70
     protection
    0.65
     fisheries
    0.64
     promotion
    0.64
     Promotion
    0.63
     proliferation
    0.62
     financing
    0.61
     betreff
    0.61
     Financing
    0.58
     strengthening
    0.57
    Activations Density 0.142%

    No Known Activations