© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 145627
    Prev
    Next
    INDEX
    Explanations

    Use certain methods

    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
    Negative Logits
     પૈ
    0.77
    packet
    0.77
    outstanding
    0.77
    pearl
    0.76
    active
    0.76
    runken
    0.76
    action
    0.75
     "+
    0.75
    нави
    0.74
     "
    0.74
    POSITIVE LOGITS
    駿
    0.75
    葶
    0.73
     놓고
    0.72
    ຽ
    0.71
     jakie
    0.68
    zos
    0.67
    တင်
    0.67
    Ẹ
    0.66
     considérée
    0.66
     Smile
    0.66
    Activations Density 0.001%

    No Known Activations