© 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. 35601
    Prev
    Next
    INDEX
    Explanations

    diagrams or illustrations

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     merve
    -1.09
    ympto
    -1.05
     résister
    -1.02
    찼
    -1.01
     utilisés
    -1.00
     به‌عنوان
    -0.99
    interesting
    -0.98
    primarily
    -0.96
     klassi
    -0.96
     soooo
    -0.95
    POSITIVE LOGITS
     where
    1.64
     diagram
    1.39
     an
    1.25
     schematic
    1.22
     with
    1.21
     three
    1.18
     drawing
    1.14
     at
    1.14
     illustrated
    1.14
     arrows
    1.13
    Activations Density 0.042%

    No Known Activations