© 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. 34465
    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
     in
    -1.63
     seven
    -1.57
     after
    -1.55
     eight
    -1.55
     three
    -1.45
     five
    -1.43
     without
    -1.42
     more
    -1.41
     every
    -1.38
     two
    -1.37
    POSITIVE LOGITS
     goofy
    1.38
     praticamente
    1.27
     vários
    1.27
     dreary
    1.27
     boister
    1.23
     wacky
    1.20
     revamped
    1.20
    riotic
    1.18
     REALLY
    1.17
     somewhat
    1.16
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.