© 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. 6204
    Prev
    Next
    INDEX
    Explanations

    multilingual text snippets

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

    The neuron primarily fires on Chinese (CJK) characters—i.e., non-Latin script text.

    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
     horribly
    0.61
    uuuu
    0.56
     terribly
    0.55
     unglaublich
    0.53
     జగ
    0.53
     horrend
    0.52
    slo
    0.52
    쫙
    0.52
     ভীষণ
    0.52
    explode
    0.52
    POSITIVE LOGITS
     Diseño
    0.68
     Prosperity
    0.67
     Pursuant
    0.66
     Corrosion
    0.64
     ดังนั้น
    0.64
     करने
    0.64
     Our
    0.63
    َّ
    0.63
     Dieses
    0.63
     Proses
    0.62
    Activations Density 0.016%

    No Known Activations