© 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. 28516
    Prev
    Next
    INDEX
    Explanations

    thank you and happy birthday

    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
     vengan
    -1.00
    最有
    -0.98
    人也
    -0.96
     verá
    -0.94
     isInitialized
    -0.93
     Ше
    -0.92
     ThemeData
    -0.92
    竈
    -0.90
    bilen
    -0.90
     только
    -0.90
    POSITIVE LOGITS
     that
    1.79
     it
    1.52
     those
    1.38
     them
    1.34
     لذلك
    1.09
    那個
    1.09
    That
    1.07
    それに
    1.06
     therefore
    1.02
     daarvoor
    1.02
    Activations Density 0.018%

    No Known Activations