© 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. 10-GEMMASCOPE-RES-131K
    7. 20388
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    őség
    -1.01
    </h1>
    -0.96
     tradizionale
    -0.94
    纽约
    -0.90
     jóvenes
    -0.87
     calça
    -0.87
     использовать
    -0.86
     viata
    -0.86
     在
    -0.86
     kormány
    -0.85
    POSITIVE LOGITS
    钓
    0.98
    らしいです
    0.95
    坝
    0.93
     originated
    0.92
    nými
    0.91
     Reprinted
    0.90
     評価
    0.90
    dica
    0.89
     Mts
    0.88
     месяцев
    0.86
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.