© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99220
    Prev
    Next
    INDEX
    Explanations

    neuron disease

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

    scientific or medical terminology related to specialized fields like neurology, astronomy, and molecular biology.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron signals the presence of domain-specific technical terms (specialized scientific or medical nouns) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     mừng
    -0.87
    Dimethyl
    -0.86
     marked
    -0.82
    멍
    -0.81
     mature
    -0.81
     modify
    -0.81
     vettoriale
    -0.80
     motorist
    -0.79
     户型
    -0.78
     sagde
    -0.78
    POSITIVE LOGITS
     Mayhem
    1.38
     Madness
    1.27
    magic
    0.95
     brille
    0.93
    OkHttpClient
    0.93
     socios
    0.93
     lavabo
    0.92
     ojo
    0.91
    еры
    0.91
     vives
    0.91
    Activations Density 0.640%

    No Known Activations