© 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. 16343
    Prev
    Next
    INDEX
    Explanations

    punctuation and list markers

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

    The neuron fires on numeric or bibliographic reference tokens—e.g. volume/page numbers or other digit‐containing items in citations.

    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
     ${
    0.62
     itself
    0.55
     existe
    0.54
    }
    0.53
     os
    0.52
    {\'
    0.52
     lui
    0.52
     {\
    0.51
    /
    0.50
     indicated
    0.50
    POSITIVE LOGITS
    Mile
    0.63
    Bromo
    0.61
    โอกาส
    0.60
     vistazo
    0.59
    Opportunities
    0.59
    Amit
    0.58
    harga
    0.57
    Mz
    0.57
    Authorities
    0.55
    挹
    0.55
    Activations Density 0.000%

    No Known Activations