© 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. 16-GEMMASCOPE-2-RES-262K
    7. 4822
    Prev
    Next
    INDEX
    Explanations

    food and tech specific noun pairings

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    i
    0.52
     inhomogeneous
    0.50
    지
    0.47
     약
    0.45
     Semiconductors
    0.44
     cytoskeleton
    0.43
    א
    0.43
    ي
    0.42
     Prepared
    0.42
     אחר
    0.42
    POSITIVE LOGITS
     voltou
    0.62
     suure
    0.59
    ни
    0.58
     pię
    0.58
    پ
    0.58
    パ
    0.58
    K
    0.58
    GeV
    0.57
     vå
    0.57
    Г
    0.57
    Activations Density 0.019%

    No Known Activations