© 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. 13003
    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
     until
    -1.00
     that
    -0.94
    専用の
    -0.90
     before
    -0.87
     Tél
    -0.83
     STUART
    -0.81
     or
    -0.81
     action
    -0.80
     devez
    -0.79
    Jen
    -0.79
    POSITIVE LOGITS
    ˄
    1.05
     exceptionally
    1.03
     tropicales
    0.99
     Rekord
    0.98
    ❙
    0.97
     alho
    0.94
     extraneous
    0.94
    Carex
    0.93
    änä
    0.93
     akti
    0.93
    Activations Density 0.000%

    No Known Activations