© 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. 31-GEMMASCOPE-2-RES-262K
    7. 109700
    Prev
    Next
    INDEX
    Explanations

    prejudice based on group membership

    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/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    us
    0.47
    nk
    0.44
     কষ্টে
    0.43
     साहस
    0.42
    ag
    0.40
    keeps
    0.40
     ଚ
    0.39
    oh
    0.39
     Costs
    0.39
    ul
    0.39
    POSITIVE LOGITS
    s
    0.57
     engender
    0.50
     masu
    0.47
     wsz
    0.44
     PERSONNEL
    0.43
     purporting
    0.43
     kodu
    0.42
     bair
    0.42
     personnel
    0.41
     presumed
    0.41
    Activations Density 0.007%

    No Known Activations