© 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. 72550
    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
     their
    -1.60
     you
    -1.48
     your
    -1.19
    You
    -1.16
     where
    -1.13
     the
    -1.09
    CardModule
    -1.00
    serviceWorker
    -1.00
     all
    -0.99
     would
    -0.99
    POSITIVE LOGITS
     renou
    1.30
    麾
    1.22
    Katalog
    1.18
    ၎
    1.16
     réessayer
    1.16
    蚨
    1.12
     rendement
    1.11
    Kuva
    1.09
    Elke
    1.09
     médicament
    1.09
    Activations Density 0.000%

    No Known Activations