© 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. 73533
    Prev
    Next
    INDEX
    Explanations

    football managers and players

    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
    ,"
    -2.17
    
    -1.93
     opérés
    -1.81
    และ
    -1.79
    ⎆
    -1.78
    attutto
    -1.73
    følge
    -1.73
    ция
    -1.71
     récemment
    -1.70
    
    -1.68
    POSITIVE LOGITS
    in
    2.09
    2
    1.77
    (
    1.64
    ?”
    1.56
    …”
    1.55
    1
    1.51
    ).”
    1.48
     ”
    1.48
    For
    1.45
    As
    1.44
    Activations Density 0.003%

    No Known Activations