© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 10327
    Prev
    Next
    INDEX
    Explanations

    punctuation and foreign characters

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

    This neuron fires most strongly on tokens that begin new sentences—i.e. punctuation marks like periods or commas and the very next word (often a discourse marker or the first word of a sentence).

    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
     которые
    0.89
     వారు
    0.89
     તેને
    0.80
     ដែល
    0.79
     ಇದನ್ನು
    0.75
     તેમને
    0.74
     които
    0.73
     обычно
    0.73
     which
    0.72
     వారికి
    0.72
    POSITIVE LOGITS
    !
    0.81
    !
    0.73
    😜
    0.71
     !
    0.68
    !“
    0.68
    !।
    0.66
    !”
    0.65
     ;-)
    0.65
    !”
    0.61
    LOL
    0.60
    Activations Density 21.279%

    No Known Activations