© 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. 16322
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on the very first substantive word of each new text segment (i.e. the initial content token after a <start>), marking paragraph or section beginnings.

    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
    }\|^{
    0.78
     complained
    0.78
     cuffs
    0.74
     angrily
    0.72
     médiocrement
    0.72
     或者
    0.71
    ,’”
    0.68
     dgn
    0.68
     payday
    0.68
     penned
    0.67
    POSITIVE LOGITS
    te
    0.73
     {}".
    0.68
     Batteries
    0.68
     Pioneers
    0.66
    et
    0.65
     Sai
    0.64
     আরও
    0.64
     Minim
    0.64
    {}".
    0.64
    in
    0.64
    Activations Density 0.000%

    No Known Activations