© 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. 147295
    Prev
    Next
    INDEX
    Explanations

    closing files

    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
     sted
    0.69
     الحس
    0.69
     anunciou
    0.68
     acquired
    0.66
     stromal
    0.66
     aplikace
    0.66
    णिज्य
    0.65
    ₆
    0.64
     লেগে
    0.63
    \,.
    0.63
    POSITIVE LOGITS
    aches
    0.69
    atch
    0.66
    acias
    0.66
    atra
    0.64
    ச்சார
    0.63
    ితే
    0.62
     ricon
    0.62
    achs
    0.61
     follow
    0.61
    acch
    0.61
    Activations Density 0.001%

    No Known Activations