© 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. 58191
    Prev
    Next
    INDEX
    Explanations

    sports teams

    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
    figure
    -0.84
    EnumMember
    -0.81
    member
    -0.77
    欵
    -0.75
    눕
    -0.74
    jö
    -0.69
    上司
    -0.69
     reúne
    -0.67
    Presentación
    -0.67
     volcán
    -0.67
    POSITIVE LOGITS
     team
    5.69
    チーム
    3.31
    team
    2.97
     teams
    2.94
     squadra
    2.91
     equipo
    2.84
     команда
    2.72
    团队
    2.53
     Team
    2.50
     squad
    2.45
    Activations Density 0.077%

    No Known Activations