© 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. 35062
    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
     its
    -1.48
     will
    -1.40
     those
    -1.29
    From
    -1.16
    Of
    -1.16
     experience
    -1.10
     continue
    -1.09
    Приятного
    -1.07
     time
    -1.05
     maintain
    -1.05
    POSITIVE LOGITS
     WHEREAS
    1.32
     logement
    1.24
     Rept
    1.20
    JDK
    1.20
     Sade
    1.20
     appels
    1.19
     ſta
    1.18
     remplacer
    1.17
    topper
    1.16
     Scu
    1.16
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.