© 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. 34-GEMMASCOPE-RES-131K
    7. 99874
    Prev
    Next
    INDEX
    Explanations

    sports statistics and leaders

    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
     reseñas
    -0.88
    printLine
    -0.86
    fromDate
    -0.85
    )();
    -0.84
    比べると
    -0.84
     plötzlich
    -0.80
     spettacolo
    -0.79
    FontAwesomeIcon
    -0.78
     = 
    -0.77
    OrFail
    -0.75
    POSITIVE LOGITS
     in
    1.27
     categories
    1.10
     averaging
    1.07
     category
    0.98
    graphique
    0.90
     leaderboard
    0.90
     Secretaría
    0.86
     among
    0.84
     average
    0.81
    Category
    0.81
    Activations Density 0.016%

    No Known Activations