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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 52789
    Prev
    Next
    INDEX
    Explanations

    Hebrew and Arabic starting letters

    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_262k_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
    si
    0.82
    stagram
    0.73
    اه
    0.73
     महिले
    0.72
    s
    0.71
     Wah
    0.71
    tract
    0.70
    akh
    0.70
    tional
    0.70
    dose
    0.66
    POSITIVE LOGITS
    LookAndFeelInfo
    0.92
     भावना
    0.81
    י
    0.73
    ཐ
    0.72
    <0xBE>
    0.71
    Transitions
    0.70
    ങ്കിലും
    0.69
    OnInit
    0.69
    板
    0.69
    zol
    0.68
    Activations Density 0.001%

    No Known Activations