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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127641
    Prev
    Next
    INDEX
    Explanations

    combat sports outcomes

    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
     masques
    -1.67
     Hift
    -1.56
     Monfieur
    -1.48
     Privac
    -1.48
    慙
    -1.47
     pcx
    -1.46
    袮
    -1.45
     boute
    -1.43
     Fichier
    -1.41
     Stande
    -1.41
    POSITIVE LOGITS
    isesi
    1.42
    SKILL
    1.40
    reportError
    1.38
    StreetMap
    1.34
    ionario
    1.34
    timiento
    1.31
    ')")
    1.30
    槤
    1.29
    rmtree
    1.29
     Олег
    1.28
    Activations Density 0.013%

    No Known Activations