© 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. 104462
    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
    无论是
    -0.97
    Regardless
    -0.94
     hvil
    -0.94
     a
    -0.93
    Amid
    -0.90
     These
    -0.88
    其他
    -0.88
    About
    -0.87
    无论
    -0.87
    Increasing
    -0.87
    POSITIVE LOGITS
     boîtier
    1.05
     suppliers
    1.01
     vedno
    1.00
    iligung
    0.99
    ("/")
    0.98
     forKey
    0.98
     fizer
    0.98
     kurulan
    0.98
    alties
    0.98
     ahora
    0.97
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.