© 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. 98533
    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
     colch
    -1.00
     Sternen
    -0.99
    是怎么回事
    -0.98
     remet
    -0.97
    siede
    -0.97
    VELOP
    -0.96
    reibung
    -0.96
     côn
    -0.96
     perí
    -0.94
    thisis
    -0.94
    POSITIVE LOGITS
    选择
    1.02
    sə
    1.00
    的选择
    0.90
     HBV
    0.90
     gefragt
    0.89
    比如
    0.85
     буква
    0.85
     erwähnten
    0.84
     verwendeten
    0.82
    ございません
    0.82
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.