© 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. 10-GEMMASCOPE-RES-131K
    7. 21725
    Prev
    Next
    INDEX
    Explanations

    hyperplasia, HEP, oper, ohyd

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

    The neuron detects medical terms related to hyperplasia and hydrological conditions in scientific text.

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

    The neuron is strongly activated by medical terms containing the “plasia” morpheme (e.g. hyperplasia, hypoplasia, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    鬭
    -2.72
    瑧
    -2.64
     摄影
    -2.50
    厨师
    -2.48
    𞤢
    -2.44
     蔬菜
    -2.41
    季節
    -2.33
    ꪔ
    -2.28
    お客
    -2.19
    {
    -2.16
    POSITIVE LOGITS
    ing
    2.81
    ⬈
    2.61
    ⚋
    2.59
     ప
    2.48
    </h1>
    2.45
     voglio
    2.41
     femeninos
    2.41
     delectable
    2.39
    five
    2.38
     saludables
    2.38
    Activations Density 0.002%

    No Known Activations