© 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. 82504
    Prev
    Next
    INDEX
    Explanations

    hyperglycemia, hyperinflation, hyperpnea

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

    The neuron detects medical and scientific terms related to "hyper" conditions, particularly hyperglyemia, hyperinflation, and other hyper- prefix medical states.

    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
    ribadian
    -0.79
    Rafael
    -0.72
    carpus
    -0.70
    jica
    -0.69
     courriel
    -0.69
     Kary
    -0.68
    ాయి
    -0.67
     Resurrection
    -0.67
    isho
    -0.67
    basePath
    -0.66
    POSITIVE LOGITS
     hyper
    5.38
    hyper
    4.47
     Hyper
    4.16
    Hyper
    4.06
     hiper
    3.16
     гипер
    3.11
     HYPER
    3.06
     Hiper
    2.00
     hyperlink
    1.90
    HY
    1.61
    Activations Density 0.078%

    No Known Activations