© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65437
    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
     JOH
    -1.25
     Japon
    -1.23
    金
    -1.21
    齮
    -1.17
    8
    -1.16
     fyr
    -1.15
    tablet
    -1.14
    japan
    -1.14
     hant
    -1.14
     vif
    -1.13
    POSITIVE LOGITS
     emphasizing
    1.27
     heightened
    1.22
     unequivocally
    1.17
     exquisite
    1.17
     devastated
    1.17
    empat
    1.16
     showcasing
    1.16
     aesthetically
    1.16
    tahui
    1.16
     emanating
    1.16
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.