© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 845
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation

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

    The neuron fires strongly on semantically rich “content” words (nouns, verbs, adjectives) rather than on common function words.

    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_31_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
     that
    0.89
     of
    0.80
     που
    0.73
     on
    0.72
     in
    0.70
     (
    0.66
     spanning
    0.65
     که
    0.65
     for
    0.64
    uels
    0.64
    POSITIVE LOGITS
    ۔۔۔۔
    0.68
    🤣🤣
    0.61
    ・・・・
    0.61
     realtà
    0.60
    。。。。
    0.60
    ;;)
    0.59
    😭😭
    0.57
     futbolista
    0.56
     personaggio
    0.56
     notizia
    0.56
    Activations Density 0.075%

    No Known Activations