© 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. 40-GEMMASCOPE-2-RES-262K
    7. 26150
    Prev
    Next
    INDEX
    Explanations

    states followed by conjunctions

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Coin
    0.39
     sh
    0.38
     Cabo
    0.38
     Sh
    0.37
    ស្ត
    0.37
     Caro
    0.37
     স্বেচ্ছাসেব
    0.37
     indicators
    0.37
     Tee
    0.36
    ਗ
    0.36
    POSITIVE LOGITS
     რომელიც
    0.61
    that
    0.61
     unmatched
    0.56
     whereby
    0.55
    urbance
    0.55
     unparalleled
    0.54
     amelyet
    0.53
     which
    0.51
     unrival
    0.51
     που
    0.51
    Activations Density 0.013%

    No Known Activations