© 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. 36521
    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
     sprüche
    -1.81
    knew
    -1.80
     rése
    -1.76
    began
    -1.73
     siè
    -1.70
    wouldn
    -1.67
    Alguna
    -1.65
    
    -1.65
     唯美
    -1.65
    Puede
    -1.65
    POSITIVE LOGITS
     has
    1.88
     on
    1.86
    w
    1.84
    _
    1.81
    y
    1.70
     D
    1.66
    h
    1.62
     -
    1.60
     out
    1.59
     T
    1.59
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.