© 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. 24-GEMMASCOPE-2-RES-16K
    7. 2083
    Prev
    Next
    INDEX
    Explanations

    german verb endings

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

    This neuron detects Persian verb morphemes—tokens like شد, می‌شود, اند, باشد, محسوب—that mark verb forms (passive, perfect, copula) in Persian 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
    повід
    0.65
    WASHINGTON
    0.58
    이랑
    0.58
    נגלית
    0.57
     sylvis
    0.55
    ⎛
    0.54
     seguintes
    0.53
    ัญลักษณ์
    0.52
    च्या
    0.52
    RAS
    0.52
    POSITIVE LOGITS
     کہ
    0.80
     که
    0.80
     وہ
    0.79
     Và
    0.77
     তবে
    0.75
     و
    0.73
    而
    0.72
     ซึ่ง
    0.70
     whereby
    0.70
     which
    0.69
    Activations Density 0.001%

    No Known Activations