© 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. 104346
    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
     after
    -2.08
     their
    -2.08
     or
    -2.08
     one
    -2.02
     impressive
    -1.88
     even
    -1.87
     huge
    -1.86
     unrelenting
    -1.85
     if
    -1.84
     before
    -1.84
    POSITIVE LOGITS
     Dinas
    2.33
     certamente
    1.99
    </i>
    1.84
     ack
    1.81
     ß
    1.79
     venus
    1.76
     majestic
    1.72
    ↵↵
    1.71
     fiasco
    1.68
     Ht
    1.67
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.