© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4474
    Prev
    Next
    INDEX
    Explanations

    currency, translation, photo, weather, site

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

    The neuron fires on text that describes downloading, linking, or embedding media files (e.g. “download …”, “linked the file or embed from YouTube”) from external sources.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    low-quality spam or auto-generated web content, particularly download sites and song lyrics pages.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    spammy web content about free media downloads/streaming and related site boilerplate (linking/hosting disclaimers, online services, and promotional pages).

    oai_token-act-pair · gpt-5Triggered 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
    െടു
    0.65
     penchant
    0.64
     enunciado
    0.59
     sophomore
    0.59
     kicker
    0.57
    摫
    0.57
     తీసుకు
    0.56
    좇
    0.56
     etched
    0.55
    était
    0.55
    POSITIVE LOGITS
    閲覧
    0.63
    たくさん
    0.63
    ＆
    0.63
     एवं
    0.62
     ਅਤੇ
    0.61
    larımız
    0.61
    gstatic
    0.59
    などの
    0.56
    жей
    0.56
    жек
    0.56
    Activations Density 0.043%

    No Known Activations