© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32724
    Prev
    Next
    INDEX
    Explanations

    Iran and Persian culture

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

    The neuron is highly sensitive to Persian/Arabic‐script tokens (i.e. non-Latin characters), activating strongly on Farsi text segments.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    بیش
    -1.27
    ساعت
    -1.24
    مرحله
    -1.16
    تصویر
    -1.14
    توضی
    -1.13
    خوب
    -1.12
    ویژگی
    -1.11
     deko
    -1.11
     musli
    -1.10
    چگونه
    -1.10
    POSITIVE LOGITS
     Persian
    1.70
     Iranian
    1.69
     Tehran
    1.68
     Iran
    1.52
    Persian
    1.45
     Mehr
    1.44
    Iranian
    1.43
     mehr
    1.29
    persian
    1.20
    Iran
    1.18
    Activations Density 0.316%

    No Known Activations