© 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. 93042
    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
     jika
    -1.07
    ein
    -1.03
     '',
    -1.02
     devine
    -1.00
     vélos
    -1.00
     chrétien
    -0.99
    📖
    -0.98
    ritsar
    -0.96
     النا
    -0.95
     لإ
    -0.95
    POSITIVE LOGITS
     quiser
    1.42
     mantuvo
    1.39
     estableció
    1.36
     entiende
    1.33
     today
    1.33
     musíte
    1.33
     subió
    1.31
    っております
    1.28
     nothing
    1.28
    さで
    1.27
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.