© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2764
    Prev
    Next
    INDEX
    Explanations

    technical programming terms

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

    The neuron detects non-English text segments, especially words in Cyrillic (and other non-Latin) scripts.

    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
     mediante
    0.61
     rechaz
    0.53
    Puede
    0.52
     aunque
    0.52
     nelle
    0.50
    르는
    0.50
    MatchType
    0.49
     는
    0.49
    STATIC
    0.49
     나누
    0.49
    POSITIVE LOGITS
     pemerintahan
    0.67
     perjalanan
    0.63
     общения
    0.62
     восстановления
    0.62
     борьбы
    0.61
     pracy
    0.61
     penggunaan
    0.60
     воздействия
    0.60
     принятия
    0.59
     współpracy
    0.59
    Activations Density 0.025%

    No Known Activations