© 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. 2623
    Prev
    Next
    INDEX
    Explanations

    Wikipedia and sister projects

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

    The neuron detects Wikipedia’s standard stub notice phrasing (e.g. “This article is a stub. You can help Wikipedia by expanding it.”).

    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
    they
    0.53
    Get
    0.53
    Y
    0.52
    令和
    0.51
    在
    0.51
    第三方
    0.50
    和
    0.50
    arif
    0.50
    铣
    0.50
    get
    0.50
    POSITIVE LOGITS
     недоста
    0.70
     Wikimedia
    0.69
     ویکی
    0.61
     Wikispecies
    0.61
     Wikipédia
    0.59
     ویکی‌پدیا
    0.59
    Wikimedia
    0.57
     недостатки
    0.57
     Вики
    0.57
     contributed
    0.56
    Activations Density 0.000%

    No Known Activations