© 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. 98944
    Prev
    Next
    INDEX
    Explanations

    young people and staff

    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
    Not in Any Lists

    No Comments

    Negative Logits
     MUNDO
    -1.22
     one
    -1.21
     if
    -1.19
     they
    -1.16
     after
    -1.14
     two
    -1.08
    -
    -1.04
    眈
    -1.02
     книгу
    -1.02
     might
    -1.02
    POSITIVE LOGITS
    ornata
    1.31
    Zobacz
    1.30
    Wednesday
    1.29
    Monday
    1.23
    Those
    1.23
     与
    1.22
     keineswegs
    1.21
     głównie
    1.21
    mainly
    1.20
     المختلفة
    1.20
    Activations Density 0.030%

    No Known Activations