© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10641
    Prev
    Next
    INDEX
    Explanations

    sitemap structure or code

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

    The neuron strongly activates on non-English, non-Latin tokens (e.g. CJK or other foreign‐script characters).

    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_31_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
    
    0.74
    ($"
    0.68
    Ча
    0.67
    Õ
    0.66
    ього
    0.65
    •
    0.64
    鹤
    0.64
    앨
    0.64
    Полу
    0.64
    Й
    0.63
    POSITIVE LOGITS
     kerana
    0.58
     till
    0.57
     she
    0.55
     että
    0.55
     அவனை
    0.54
     because
    0.52
     by
    0.52
     but
    0.52
     seorang
    0.52
     he
    0.52
    Activations Density 0.000%

    No Known Activations