© 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. 577
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on transliterated Arabic personal names and honorific/title tokens (i.e. proper names in Arabic script form).

    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
     _____________
    0.67
     ainda
    0.64
     importanti
    0.63
     mydict
    0.61
     atributo
    0.60
     pemain
    0.60
     ____________
    0.60
     millilit
    0.59
     hebben
    0.59
     hadden
    0.58
    POSITIVE LOGITS
    H
    0.73
    J
    0.73
    V
    0.71
    P
    0.69
    D
    0.68
    Error
    0.67
    Y
    0.67
    T
    0.67
    X
    0.66
    C
    0.66
    Activations Density 0.243%

    No Known Activations