© 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. 7409
    Prev
    Next
    INDEX
    Explanations

    transform(-50%, -50%)

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

    The neuron is a detector for Cyrillic letters (i.e. non-Latin characters), strongly activating on the Cyrillic characters “о,” “у,” etc.

    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
    ра
    0.88
    ي
    0.83
    rául
    0.78
    ি
    0.75
    ار
    0.71
     capitalization
    0.70
    йся
    0.70
    يي
    0.68
    SCE
    0.68
    æg
    0.67
    POSITIVE LOGITS
     nombr
    0.89
     Đ
    0.82
     derive
    0.79
     ⠀
    0.79
     tokamak
    0.79
     Độ
    0.78
     ⚫
    0.77
     Từ
    0.76
     ⋅
    0.74
     treten
    0.73
    Activations Density 0.001%

    No Known Activations