© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 3993
    Prev
    Next
    INDEX
    Explanations

    Arabic conversational phrases

    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
     تو
    0.87
     تُ
    0.87
     تضم
    0.86
     خلال
    0.86
    ت
    0.84
    ًا
    0.83
     ت
    0.81
     تم
    0.80
    ﺗ
    0.79
     مجموعة
    0.76
    POSITIVE LOGITS
     Beautiful
    0.79
     Enter
    0.78
     beautiful
    0.75
     Very
    0.75
     plek
    0.74
     frumo
    0.72
     vostri
    0.72
     Always
    0.70
     gentlemen
    0.70
     Sweet
    0.69
    Activations Density 0.004%

    No Known Activations