© 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. 147486
    Prev
    Next
    INDEX
    Explanations

    шаг 1

    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
    /\/
    0.79
    oncesto
    0.76
     gehören
    0.75
    курс
    0.74
    เภท
    0.74
    CHCl
    0.73
    Ӣ
    0.73
    iciencies
    0.72
     แก
    0.71
     acara
    0.71
    POSITIVE LOGITS
     desirable
    0.85
     right
    0.80
     traction
    0.78
    lr
    0.77
     Atom
    0.76
     autod
    0.72
    o
    0.72
     Mans
    0.72
     Right
    0.71
    льной
    0.70
    Activations Density 0.001%

    No Known Activations