© 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. 7477
    Prev
    Next
    INDEX
    Explanations

    language identification or translation

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

    This neuron strongly activates on non‐Latin (East Asian) script tokens—Chinese characters, Japanese kana/kanji, or Korean Hangul.

    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
     اولا
    0.67
     Сьогодні
    0.65
     בש
    0.64
     уены
    0.63
    をし
    0.60
     amidst
    0.60
     whereupon
    0.59
    Dopo
    0.57
    uhnya
    0.57
     Khi
    0.56
    POSITIVE LOGITS
    意味着
    0.71
     कोई
    0.70
     herhangi
    0.68
    它
    0.67
     travaille
    0.64
     يمكن
    0.64
     অনুরূপ
    0.63
    க்கப்பட்டது
    0.63
    herb
    0.63
    任意の
    0.62
    Activations Density 0.001%

    No Known Activations