© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 66081
    Prev
    Next
    INDEX
    Explanations

    narcolepsy and orexin

    np_acts-logits-general · gemini-2.5-flash-lite

    medical terminology and condition names, particularly focusing on neurological disorders like narcolepsy and restless legs syndrome.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     revolutionaries
    -0.79
     支援
    -0.73
     really
    -0.73
     triglycerides
    -0.69
     deeply
    -0.69
     emphasized
    -0.69
     highlighted
    -0.68
    لهم
    -0.68
    Celular
    -0.68
     deposito
    -0.68
    POSITIVE LOGITS
     sleepy
    1.13
    SLEEP
    1.09
     SLEEP
    1.07
     Sleep
    1.05
     خواب
    1.02
     nar
    1.01
     Rechts
    0.97
    sleep
    0.92
    Sleep
    0.90
     sleepers
    0.87
    Activations Density 0.070%

    No Known Activations