© 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. 11789
    Prev
    Next
    INDEX
    Explanations

    Chinese URLs and technical terms

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

    The neuron flags commercial or promotional language—particularly product/company names, financial terms, prices, and other ad-style jargon.

    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
     asimismo
    0.71
     enzimas
    0.70
    𝖾
    0.64
     Asimismo
    0.63
     FIGURES
    0.62
     [&](
    0.61
    identifiers
    0.61
     carrinho
    0.61
     કાર્
    0.59
     aces
    0.59
    POSITIVE LOGITS
    修改
    0.55
    人民
    0.54
    网
    0.54
    庸
    0.53
    大学生
    0.52
     violently
    0.50
    头
    0.50
    帮助
    0.49
    次
    0.48
    瓦
    0.48
    Activations Density 0.069%

    No Known Activations