© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8916
    Prev
    Next
    INDEX
    Explanations

    specific punctuation followed by word

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

    The neuron detects non-English (foreign) text segments, especially words or tokens with diacritics or in other scripts.

    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
    вшей
    0.76
    сии
    0.75
    сков
    0.74
    approved
    0.74
    Missense
    0.73
     оценки
    0.73
    щей
    0.71
    수인
    0.71
    TARIFF
    0.70
    способ
    0.70
    POSITIVE LOGITS
     jonka
    0.80
    al
    0.77
    ،
    0.75
     ،
    0.74
     joka
    0.73
     ـ
    0.69
    ek
    0.68
     még
    0.68
     yani
    0.68
     mutta
    0.67
    Activations Density 0.001%

    No Known Activations