© 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. 12583
    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
    ziu
    -1.02
    私人
    -1.02
     esperienza
    -0.98
     because
    -0.95
     aranha
    -0.94
    ėse
    -0.94
    vantages
    -0.92
     perfectamente
    -0.91
    Syria
    -0.91
     alumínio
    -0.91
    POSITIVE LOGITS
    miques
    1.04
    rzysz
    1.01
     Meningkatkan
    0.98
    '}';
    0.94
    omás
    0.94
     сможет
    0.93
     säs
    0.93
    ฤษ
    0.93
     kvä
    0.93
    ým
    0.92
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.