© 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. 12809
    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
    *?
    -0.98
     treino
    -0.97
     deutschland
    -0.96
    btnut
    -0.95
     gefe
    -0.94
     Uniwers
    -0.92
     Incluso
    -0.92
     daga
    -0.91
    トッピング
    -0.91
     gql
    -0.90
    POSITIVE LOGITS
     main
    0.89
     Hamlin
    0.88
     venture
    0.86
     formal
    0.84
     guarda
    0.84
    autorelease
    0.84
     podemos
    0.82
     and
    0.82
    肯定是
    0.82
     emp
    0.80
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.