© 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. 13017
    Prev
    Next
    INDEX
    Explanations

    words preceding punctuation

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

    The neuron fires on the very first content word that begins a new sentence (i.e. sentence-initial tokens).

    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
     세포
    0.84
     黒
    0.83
    ᐟ
    0.81
     ۽
    0.79
     Ս
    0.78
     багато
    0.77
     н
    0.77
     ム
    0.77
     Sergei
    0.77
     Многие
    0.76
    POSITIVE LOGITS
    SaveChanges
    0.71
    Chars
    0.70
    ти
    0.68
    นั่ง
    0.68
    CriteriaUtils
    0.68
    бира
    0.67
    Req
    0.66
    бель
    0.66
    Choices
    0.65
     vínculos
    0.64
    Activations Density 0.000%

    No Known Activations