© 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. 12613
    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
     where
    -1.11
     its
    -1.09
     by
    -1.02
     lju
    -0.99
     whereas
    -0.99
     turist
    -0.97
     personnage
    -0.94
     having
    -0.91
     autonome
    -0.91
     bazar
    -0.90
    POSITIVE LOGITS
    eventually
    1.09
     których
    1.07
     větší
    1.03
     irgendwann
    1.02
     Erişim
    1.00
     которые
    0.99
     Schließlich
    0.97
     sonunda
    0.96
    Eventually
    0.94
     incluye
    0.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.