© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130424
    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
    eeqa
    -1.13
    kün
    -1.13
    flyer
    -1.04
    krát
    -1.02
     vulgaires
    -1.00
    ؤول
    -0.96
    Šalt
    -0.95
     had
    -0.93
     śnie
    -0.93
     one
    -0.92
    POSITIVE LOGITS
    ͛
    1.09
     but
    1.09
     сейчас
    1.07
     geniş
    1.05
     proiect
    1.02
     paciencia
    0.99
     sommige
    0.98
    メニューは
    0.97
    uerung
    0.96
    weisung
    0.96
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.