© 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. 13106
    Prev
    Next
    INDEX
    Explanations

    objects erstellen, Welt erzielt, riss verlaufen

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

    This neuron detects words written in Persian script.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    non-English text, particularly in Persian, Arabic, German, Portuguese, Spanish, and other non-Latin scripts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    Persian (Farsi) language text, especially common function words and affixes, indicating detection of Farsi passages.

    oai_token-act-pair · gpt-5Triggered 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
    他是
    0.71
     použití
    0.66
     letech
    0.65
     అతను
    0.64
     zásobníku
    0.62
     rupam
    0.62
     gustaría
    0.62
     tejto
    0.62
     hänen
    0.61
     případě
    0.61
    POSITIVE LOGITS
     GLE
    0.65
     (
    0.62
     ме
    0.62
     или
    0.55
     вече
    0.55
     in
    0.55
     Committed
    0.55
     DREAM
    0.54
     or
    0.54
     atau
    0.54
    Activations Density 0.000%

    No Known Activations