© 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. 114238
    Prev
    Next
    INDEX
    Explanations

    company designations

    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
     französische
    -1.48
     usado
    -1.47
     a
    -1.31
     about
    -1.29
     colorida
    -1.25
     locul
    -1.23
     doméstico
    -1.20
    肯定是
    -1.16
     nowy
    -1.15
     montaje
    -1.14
    POSITIVE LOGITS
    There
    1.41
    لاحظ
    1.32
    zeugung
    1.32
     incess
    1.30
    Some
    1.30
     після
    1.27
    Παρα
    1.24
    henswürdigkeiten
    1.23
    Although
    1.22
    Through
    1.21
    Activations Density 0.055%

    No Known Activations