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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66809
    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
     both
    -1.34
     all
    -1.33
     as
    -1.30
     without
    -1.30
     their
    -1.21
     because
    -1.20
     how
    -1.20
     first
    -1.17
     superbly
    -1.14
     on
    -1.13
    POSITIVE LOGITS
     wacky
    1.32
    specifically
    1.20
     relentless
    1.20
     momentous
    1.17
     quirky
    1.16
     wondrous
    1.15
     lauded
    1.15
     marvelous
    1.13
     renowned
    1.13
     ridiculously
    1.13
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.