© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 7231
    Prev
    Next
    INDEX
    Explanations

    three.js renderer

    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
    |()
    -0.90
    的所有
    -0.81
    átku
    -0.77
     discapacidad
    -0.73
    dui
    -0.72
    特殊
    -0.71
    quial
    -0.71
     مع
    -0.71
    lename
    -0.71
     Generation
    -0.70
    POSITIVE LOGITS
     renderer
    0.97
     Stats
    0.92
    Stats
    0.88
    composer
    0.87
    渲染
    0.85
    stats
    0.81
     Pointer
    0.80
    renderer
    0.79
     Фі
    0.79
     animate
    0.78
    Activations Density 0.021%

    No Known Activations