© 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. 16128
    Prev
    Next
    INDEX
    Explanations

    foreign languages and words

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

    The neuron strongly activates on ellipsis sequences (“...”), i.e. runs of three or more dots indicating a pause or omission.

    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
    י
    0.67
    o
    0.65
    ন
    0.63
    в
    0.61
    ה
    0.61
    וי
    0.60
    us
    0.59
    স
    0.57
    st
    0.56
    <0x88>
    0.55
    POSITIVE LOGITS
     nyata
    0.77
    อย่าง
    0.76
     sosok
    0.75
     berubah
    0.73
     blatantly
    0.72
     zaś
    0.70
     magnifique
    0.70
     wartości
    0.70
    ujące
    0.68
     símbolos
    0.67
    Activations Density 0.000%

    No Known Activations