© 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. 74545
    Prev
    Next
    INDEX
    Explanations

    performing marriage ceremonies

    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
    Scotland
    0.47
    생
    0.46
    цтва
    0.46
    영상
    0.44
     источник
    0.43
     времени
    0.43
    ume
    0.42
     монта
    0.42
    협
    0.42
     இடம்
    0.42
    POSITIVE LOGITS
     Etsy
    0.54
     same
    0.47
     smart
    0.46
     gray
    0.46
     neighborhoods
    0.46
     de
    0.45
     drugstore
    0.45
     correo
    0.45
     sourdough
    0.44
     Salesforce
    0.44
    Activations Density 0.006%

    No Known Activations