© 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. 16262
    Prev
    Next
    INDEX
    Explanations

    AngelList, Crowdfunding, Investing

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

    The neuron fires strongly on specialized content words—proper names, technical terms, or domain‐specific jargon—regardless of the topic.

    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
     Expt
    0.63
     Motel
    0.63
     Survey
    0.59
    mitz
    0.59
     島
    0.57
     Chaplain
    0.57
     Women
    0.56
    ｴ
    0.56
     Improvements
    0.56
    ennis
    0.55
    POSITIVE LOGITS
    🤭
    0.71
    🤯
    0.70
     metaverse
    0.68
    或者
    0.68
    🥳
    0.66
     underwhelming
    0.65
    https
    0.61
     otherworldly
    0.61
     cryptocur
    0.59
     multiverse
    0.59
    Activations Density 0.005%

    No Known Activations