© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 149443
    Prev
    Next
    INDEX
    Explanations

    streamlit and similar imports

    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
     නැ
    0.67
     integer
    0.67
     prins
    0.65
    љи
    0.65
    ค
    0.64
     दिला
    0.64
     ιστο
    0.63
    দি
    0.63
     morti
    0.62
     Pounds
    0.62
    POSITIVE LOGITS
    unset
    0.73
    unning
    0.68
    бов
    0.65
     تا
    0.65
    esson
    0.63
    yrıca
    0.63
    ussi
    0.62
    amentul
    0.62
    ('${
    0.61
     شمال
    0.61
    Activations Density 0.001%

    No Known Activations