© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 7086
    Prev
    Next
    INDEX
    Explanations

    matrix operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     bronchi
    1.35
     crem
    1.33
     nicotine
    1.31
     bub
    1.25
     Alpen
    1.25
     Streams
    1.24
     inhaling
    1.24
    aceans
    1.24
    糰
    1.23
    unsubscribe
    1.23
    POSITIVE LOGITS
     determinante
    2.05
    matrices
    1.97
     Matrices
    1.91
     MATRIX
    1.88
    Matrices
    1.83
     матри
    1.79
     determinant
    1.75
    MATRIX
    1.73
     Matrix
    1.73
     matrice
    1.72
    Activations Density 0.015%

    No Known Activations