© 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. 25547
    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
     may
    -1.28
     comes
    -1.27
     then
    -1.24
     just
    -1.21
     does
    -1.19
    cadas
    -1.18
    there
    -1.18
     gets
    -1.17
     brings
    -1.17
     serves
    -1.16
    POSITIVE LOGITS
     trône
    1.34
     refroid
    1.21
     vieron
    1.20
    albeit
    1.17
     contribuer
    1.16
    あー
    1.16
    こともあり
    1.13
     különböző
    1.09
     delikat
    1.09
    happily
    1.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.