© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72156
    Prev
    Next
    INDEX
    Explanations

    ternary operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     and
    -1.73
    Introdução
    -1.38
     from
    -1.29
    7
    -1.27
     তার
    -1.27
    Both
    -1.26
     років
    -1.24
     by
    -1.24
    6
    -1.23
     both
    -1.22
    POSITIVE LOGITS
     a
    1.93
     we
    1.79
     representing
    1.47
     are
    1.44
     other
    1.38
     will
    1.37
     circumstances
    1.36
     emite
    1.34
    而非
    1.34
    を行います
    1.34
    Activations Density 0.005%

    No Known Activations