© 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. 34-GEMMASCOPE-RES-131K
    7. 48478
    Prev
    Next
    INDEX
    Explanations

    team player season

    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_34/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
    сий
    -0.92
     Perú
    -0.88
    ױ
    -0.86
     तीन
    -0.85
    piecz
    -0.85
    ƚ
    -0.85
     candidato
    -0.84
    obenz
    -0.83
    рабаты
    -0.83
     vzor
    -0.83
    POSITIVE LOGITS
     team
    2.91
     teams
    2.44
     players
    2.41
     player
    2.39
     league
    2.20
     season
    2.06
     championship
    1.88
     games
    1.82
     opponents
    1.80
     tournament
    1.78
    Activations Density 0.035%

    No Known Activations