© 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. 7715
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on title‐case or headline words—i.e. capitalized keywords that signal book, article, or section titles.

    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
    َّة
    0.64
    ޤ
    0.64
    හා
    0.61
    isierten
    0.61
    ಓ
    0.61
    ڌ
    0.61
    өз
    0.60
    يك
    0.60
     تاريخ
    0.60
    чила
    0.60
    POSITIVE LOGITS
    !
    0.86
     শীর্ষক
    0.79
     GmbH
    0.77
    !:
    0.74
    !-
    0.73
    !'
    0.71
    株式会社
    0.71
    이라는
    0.71
     라는
    0.70
    ®
    0.69
    Activations Density 0.175%

    No Known Activations