© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 98665
    Prev
    Next
    INDEX
    Explanations

    Grand Prix car models

    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_22/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
     cantit
    -0.94
    の特徴
    -0.94
    ovy
    -0.88
     zufrieden
    -0.87
     căr
    -0.86
    quran
    -0.86
     mainline
    -0.85
     Tagged
    -0.82
     fiecare
    -0.81
     dernières
    -0.80
    POSITIVE LOGITS
     what
    1.08
     this
    1.02
     helps
    0.93
     with
    0.91
     to
    0.90
     without
    0.88
     aptly
    0.87
     one
    0.86
    ía
    0.83
     sehr
    0.82
    Activations Density 0.044%

    No Known Activations