© 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. 28340
    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
     asfal
    -1.21
     frek
    -1.18
     Zá
    -1.08
    WAUKEE
    -1.05
    ocl
    -1.05
     moft
    -1.04
     OSError
    -1.04
     zape
    -1.01
    рии
    -1.01
    २
    -1.00
    POSITIVE LOGITS
    küche
    1.13
    Marque
    1.08
    各種
    1.06
     scurt
    1.04
    Добрый
    1.03
    メリカ
    1.03
    ro
    1.03
    ovala
    1.02
     Bestimmungen
    1.02
    Huhu
    1.02
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.