© 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. 22-GEMMASCOPE-RES-131K
    7. 130962
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     after
    -1.84
     undeniably
    -1.74
     for
    -1.71
     unrelenting
    -1.70
     facilitating
    -1.55
     purposefully
    -1.54
     only
    -1.54
     massively
    -1.52
     consistently
    -1.51
     furthering
    -1.50
    POSITIVE LOGITS
     Dinas
    1.68
    
    1.60
     trám
    1.45
     ček
    1.43
    every
    1.41
    Etimología
    1.40
    aning
    1.39
    commonly
    1.37
     revisa
    1.37
    composed
    1.37
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.