© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 35342
    Prev
    Next
    INDEX
    Explanations

    ERISA and retirement plans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     продук
    0.42
     محصول
    0.40
     Landry
    0.40
     maal
    0.39
    LinkClicked
    0.39
    癀
    0.38
    贴
    0.38
    驩
    0.38
     Guil
    0.38
    mDatas
    0.38
    POSITIVE LOGITS
     ERISA
    0.81
     fiduciary
    0.71
     administrator
    0.64
     trustee
    0.63
    iduciary
    0.62
     Administrator
    0.61
    Administrator
    0.58
    administrator
    0.58
     administrators
    0.55
    Participant
    0.54
    Activations Density 0.002%

    No Known Activations