© 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. 41-GEMMASCOPE-2-RES-262K
    7. 35204
    Prev
    Next
    INDEX
    Explanations

    matrix and array structures

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Giá
    0.40
     Decomposition
    0.40
    胼
    0.39
     Idi
    0.39
     Diagonal
    0.39
     Religion
    0.38
     Coron
    0.38
     Due
    0.38
     Kā
    0.38
     Oko
    0.38
    POSITIVE LOGITS
    rectangular
    0.55
     rectangular
    0.48
    排列
    0.48
    grid
    0.47
    数组
    0.47
    陣
    0.46
     matrix
    0.45
    array
    0.44
    Matrix
    0.44
     прямоуго
    0.44
    Activations Density 0.003%

    No Known Activations