© 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. 3018
    Prev
    Next
    INDEX
    Explanations

    relative pronouns

    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
    imerk
    0.25
     olmadan
    0.24
     ہوگا۔
    0.24
    .\\
    0.24
     произошло
    0.23
    。
    0.23
     Afterwards
    0.22
    ก่อน
    0.22
    *.
    0.22
    ؟
    0.22
    POSITIVE LOGITS
     that
    0.73
     που
    0.68
     که
    0.67
     которые
    0.63
     الذي
    0.62
     التي
    0.59
     whose
    0.58
     which
    0.56
    that
    0.55
     yang
    0.55
    Activations Density 0.865%

    No Known Activations