© 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. 15884
    Prev
    Next
    INDEX
    Explanations

    list separators and conjunctions

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

    The neuron fires on section‐ or metadata‐style labels and tags (e.g. category names, post tags, figure labels, and other document metadata markers).

    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
    это
    0.69
    就已经
    0.66
    го
    0.66
     είναι
    0.64
     был
    0.63
    不是
    0.61
    количество
    0.61
     був
    0.59
    ádza
    0.59
    并不是
    0.58
    POSITIVE LOGITS
     Aank
    0.78
     থাকিলে
    0.73
     Afternoon
    0.72
     及び
    0.71
     Lemmas
    0.70
     Theorems
    0.69
     Entries
    0.68
     Oliva
    0.68
     respectively
    0.68
     أيضًا
    0.68
    Activations Density 0.239%

    No Known Activations