© 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. 26438
    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
    しと
    -1.48
     every
    -1.37
     menetap
    -1.31
     achieve
    -1.28
     all
    -1.28
    وقع
    -1.28
     one
    -1.27
     from
    -1.23
     in
    -1.23
     with
    -1.21
    POSITIVE LOGITS
     myriad
    1.77
    nade
    1.40
     wondrous
    1.36
     adorned
    1.34
     amd
    1.31
    colección
    1.29
     "
    1.27
     ation
    1.26
     diversos
    1.26
    mentioned
    1.26
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.