© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130151
    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
     for
    -2.45
     provide
    -2.39
     Perhaps
    -2.33
     Some
    -2.31
     before
    -2.31
     When
    -2.30
     their
    -2.25
     Usually
    -2.25
     Ironically
    -2.23
     after
    -2.22
    POSITIVE LOGITS
     delightfully
    2.39
     ridiculously
    2.23
     wonderfully
    2.19
     alluring
    2.14
     vijf
    2.13
     decidedly
    2.13
     strikingly
    2.08
     astounding
    2.06
     Dinas
    2.06
     vastly
    2.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.