© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27717
    Prev
    Next
    INDEX
    Explanations

    team and collective action

    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
    íodo
    -0.94
    ॥
    -0.94
     jag
    -0.92
    Zig
    -0.90
    лец
    -0.87
    🔁
    -0.87
    pova
    -0.82
     aynı
    -0.81
     quien
    -0.81
    TextBoxColumn
    -0.80
    POSITIVE LOGITS
     team
    2.66
    team
    1.89
     group
    1.84
     we
    1.80
     teamwork
    1.66
    Team
    1.58
     collectively
    1.57
    团队
    1.56
     collective
    1.52
     Team
    1.50
    Activations Density 0.129%

    No Known Activations