© 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. 68392
    Prev
    Next
    INDEX
    Explanations

    asking questions or nature

    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
     când
    -1.44
    obiettivo
    -1.38
    unità
    -1.24
    accordo
    -1.23
    €™
    -1.23
    only
    -1.23
    incontro
    -1.23
    今では
    -1.21
     tylko
    -1.21
     only
    -1.20
    POSITIVE LOGITS
     pense
    1.25
    Халы
    1.20
    Smoke
    1.18
     $("#
    1.17
     significado
    1.16
     zou
    1.16
     or
    1.16
     pié
    1.15
     RoutedEventArgs
    1.15
     to
    1.14
    Activations Density 0.095%

    No Known Activations