© 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. 53-GEMMASCOPE-2-RES-262K
    7. 50562
    Prev
    Next
    INDEX
    Explanations

    conjunctions and contrasts

    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_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Those
    0.45
     ۔
    0.43
    Seal
    0.42
     তিনি
    0.41
     يُ
    0.41
    Men
    0.41
     التح
    0.41
     بالت
    0.41
     ktorá
    0.41
     त्यांनी
    0.40
    POSITIVE LOGITS
    还需要
    0.53
    还能
    0.52
     just
    0.51
    既
    0.50
    还会
    0.47
    还不
    0.47
    just
    0.46
    却
    0.45
     still
    0.45
    可能
    0.45
    Activations Density 0.001%

    No Known Activations