© 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. 47561
    Prev
    Next
    INDEX
    Explanations

    wrestle or competed

    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
     assignments
    -0.80
     Officers
    -0.75
    officer
    -0.72
     officer
    -0.71
     ASSIGN
    -0.69
    Klo
    -0.69
     Officer
    -0.68
     officers
    -0.68
    ارف
    -0.67
    hadores
    -0.67
    POSITIVE LOGITS
     room
    0.79
     wrestle
    0.78
    partners
    0.73
     ולה
    0.71
    球队
    0.71
    Room
    0.71
    tsburgh
    0.70
     wrestlers
    0.69
    mies
    0.69
     depends
    0.68
    Activations Density 0.023%

    No Known Activations