© 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-262K
    7. 147640
    Prev
    Next
    INDEX
    Explanations

    save code as .cpp

    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
     Acts
    0.73
     localizado
    0.72
    ↞
    0.69
    ణి
    0.68
    بط
    0.67
     ہو۔
    0.66
    nehmer
    0.65
     oure
    0.65
    ολ
    0.64
     বিচার
    0.64
    POSITIVE LOGITS
     сход
    0.76
     쓰고
    0.71
    subTest
    0.71
    정과
    0.69
    وضع
    0.69
     Uses
    0.68
     ･
    0.68
    밑
    0.68
     PVC
    0.66
    asus
    0.66
    Activations Density 0.001%

    No Known Activations