© 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. 45728
    Prev
    Next
    INDEX
    Explanations

    possessive 's

    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
     materie
    -1.30
     remercier
    -1.28
    Organizador
    -1.26
     mambo
    -1.20
     tyran
    -1.20
    Rifer
    -1.20
    ストレッチ
    -1.19
    軽量
    -1.19
     sportage
    -1.18
     fabia
    -1.17
    POSITIVE LOGITS
     including
    1.48
     is
    1.27
     it
    1.27
     to
    1.25
    :
    1.21
    莘
    1.20
     [
    1.20
    ’
    1.18
    外の
    1.17
     an
    1.14
    Activations Density 0.063%

    No Known Activations