© 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. 147449
    Prev
    Next
    INDEX
    Explanations

    Open Courseware or French names

    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
    höhe
    0.76
    звичай
    0.71
    फरी
    0.70
    rifle
    0.70
     />';
    0.70
    usan
    0.70
    ifle
    0.69
    anten
    0.68
    <unused1028>
    0.67
    茶
    0.67
    POSITIVE LOGITS
     Play
    0.79
     Austin
    0.74
     Shell
    0.74
     play
    0.72
     login
    0.70
     উত্তেজ
    0.70
    avelin
    0.69
    шко
    0.69
     Please
    0.68
     HTTP
    0.68
    Activations Density 0.001%

    No Known Activations