© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129589
    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
     all
    -2.03
     over
    -1.97
     more
    -1.97
     with
    -1.95
     on
    -1.94
     in
    -1.88
     one
    -1.88
     should
    -1.80
     at
    -1.80
     epitom
    -1.73
    POSITIVE LOGITS
     comportements
    1.76
    ܆
    1.61
     horrend
    1.55
    ￪
    1.54
     illi
    1.54
     marvelous
    1.53
     mélang
    1.53
    都已经
    1.51
     COULD
    1.51
     magnific
    1.49
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.