© 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. 68651
    Prev
    Next
    INDEX
    Explanations

    links, email addresses, and tags

    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
     is
    -1.71
     When
    -1.55
     But
    -1.45
     in
    -1.44
     because
    -1.38
     so
    -1.38
     and
    -1.32
     More
    -1.30
     As
    -1.29
     If
    -1.28
    POSITIVE LOGITS
    ísimas
    1.78
    atized
    1.70
    atization
    1.59
    omorphisms
    1.57
    really
    1.52
    yship
    1.48
    lllllll
    1.47
     kanak
    1.47
     alpes
    1.45
    riy
    1.44
    Activations Density 0.062%

    No Known Activations