© 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. 79917
    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
     to
    -2.50
     on
    -2.08
     in
    -2.06
     by
    -1.94
     one
    -1.91
     for
    -1.87
     all
    -1.86
     every
    -1.74
     out
    -1.74
     as
    -1.72
    POSITIVE LOGITS
     acuerdos
    1.63
     Dinas
    1.55
     strikingly
    1.48
     เปิด
    1.47
     éviter
    1.45
     apprécier
    1.45
    뭄
    1.44
     étudier
    1.42
     함수
    1.42
     acclaimed
    1.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.