© 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. 54255
    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
    (&:
    -1.03
     you
    -0.99
    笑容
    -0.94
     :
    -0.93
    didSet
    -0.93
    ttää
    -0.91
     polícia
    -0.90
     suivants
    -0.89
    brief
    -0.88
     conhe
    -0.87
    POSITIVE LOGITS
    enlace
    1.07
     makkelijk
    1.02
    ❼
    1.00
    Lego
    0.99
    compra
    0.98
    empresa
    0.96
    geschoss
    0.96
    partes
    0.95
     meestal
    0.94
     gemakkelijk
    0.94
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.