© 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. 33294
    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
     algas
    -1.23
     twenty
    -1.23
     prominent
    -1.13
    شفى
    -1.13
     corredores
    -1.12
     bordado
    -1.12
    ksamkeit
    -1.10
    棐
    -1.10
     noteworthy
    -1.09
     médec
    -1.08
    POSITIVE LOGITS
    3
    1.27
     to
    1.19
    8
    1.14
     gesuchten
    1.08
     fortsatt
    1.05
     firs
    1.05
     Khrushchev
    1.05
    0
    1.05
     ganancia
    1.05
    u
    1.03
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.