© 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. 68018
    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
    marion
    -1.12
     this
    -1.00
     defendant
    -0.93
     Branchen
    -0.93
     darbo
    -0.92
     papild
    -0.91
    nikon
    -0.88
     tradition
    -0.88
     森
    -0.88
     茶
    -0.87
    POSITIVE LOGITS
    ชาติ
    0.95
     antlers
    0.95
    Falta
    0.94
     eventually
    0.93
    Kritik
    0.93
    Parece
    0.93
     chisel
    0.92
    It
    0.90
     we
    0.89
     stesse
    0.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.