Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 1540
    Prev
    Next
    INDEX
    Explanations

    Arabic words, especially with prefixes like "ال", "الم", "المت"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ele
    0.75
     caudal
    0.74
     compris
    0.73
    gestion
    0.73
     ಹೆಚ್ಚಿನ
    0.72
    鬯
    0.72
    ًا
    0.72
    ствием
    0.72
     opérateur
    0.71
    🕯
    0.71
    POSITIVE LOGITS
     المختلفة
    1.08
     المت
    0.99
     الأخرى
    0.97
     المست
    0.95
     التي
    0.92
     التى
    0.92
     الجديدة
    0.88
     الت
    0.85
     التالية
    0.84
     المطل
    0.82
    Activations Density 0.044%

    No Known Activations