© 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. 10-GEMMASCOPE-RES-131K
    7. 47571
    Prev
    Next
    INDEX
    Explanations

    json objects in arrays

    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
     these
    -1.94
     all
    -1.83
     first
    -1.80
    first
    -1.75
     only
    -1.73
     if
    -1.59
    the
    -1.58
     with
    -1.53
     it
    -1.52
     will
    -1.52
    POSITIVE LOGITS
     réparation
    1.50
     Traducción
    1.47
     Algunos
    1.47
     mejoras
    1.43
    endless
    1.41
    もあった
    1.40
     นัก
    1.39
    joueurs
    1.38
    mvh
    1.37
     parroquia
    1.35
    Activations Density 0.039%

    No Known Activations