© 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. 7867
    Prev
    Next
    INDEX
    Explanations

    non-English words or technical terms

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

    This neuron lights up on unusually rare or low‐frequency tokens in the 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
    u
    1.03
     자료
    0.89
     morrer
    0.78
     limestone
    0.78
    いが
    0.77
     manter
    0.74
    ا
    0.73
     제한
    0.73
     pretzels
    0.73
     سوف
    0.72
    POSITIVE LOGITS
    Це
    0.91
    ടുത്ത
    0.86
    ︎
    0.83
    Мен
    0.80
    Наша
    0.75
    Компания
    0.75
    te
    0.74
    Ч
    0.74
    На
    0.73
    ּ
    0.72
    Activations Density 0.000%

    No Known Activations