© 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. 10062
    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
    м
    -1.34
    e
    -1.25
     In
    -1.23
    E
    -1.22
     щ
    -1.21
     IN
    -1.16
     allow
    -1.14
     ,
    -1.13
     város
    -1.11
    m
    -1.11
    POSITIVE LOGITS
     to
    1.45
    ⋰
    1.27
    
    1.25
    varios
    1.23
    buon
    1.20
     經典
    1.20
     餐廳
    1.20
    रीद
    1.18
    ...'
    1.16
     ぬいぐるみ
    1.16
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.