© 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. 28648
    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
     first
    -1.27
     facilitating
    -1.19
    ֢
    -1.18
     until
    -1.15
     during
    -1.13
     their
    -1.12
     adorno
    -1.12
    iramente
    -1.11
     phénom
    -1.11
     capabilities
    -1.11
    POSITIVE LOGITS
     to
    1.16
     カットソー
    1.08
     adecuados
    1.05
     geliefert
    1.05
     Akufo
    1.05
     ____________
    1.04
     REALLY
    1.04
     Dinas
    1.02
    辊
    1.02
     deline
    1.00
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.