© 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. 104124
    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
     cilind
    -1.50
    くちゃ
    -1.39
     that
    -1.38
     intermedia
    -1.37
     have
    -1.34
     pompa
    -1.32
    的吗
    -1.30
    
    -1.29
    かもし
    -1.29
    ？」
    -1.27
    POSITIVE LOGITS
    ák
    1.33
     Когда
    1.27
     király
    1.26
    自己是
    1.23
    人是
    1.22
    砹
    1.20
    人也
    1.20
     rst
    1.20
    శ
    1.20
    When
    1.19
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.