© 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. 34-GEMMASCOPE-RES-131K
    7. 23511
    Prev
    Next
    INDEX
    Explanations

    esophageal reflux and regurgitation

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

    This neuron identifies medical terms related to gastrointestinal conditions, particularly gastroesophageal reflux and regurgitation.

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

    The neuron strongly activates on technical terms naming acid‐related gastrointestinal disorders (e.g. “acid,” “gastroesophageal,” “reflux,” “esophagitis,” “peptic ulcer”).

    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
     riddles
    -0.79
    ändert
    -0.78
     devaluation
    -0.76
    NGS
    -0.76
     punctures
    -0.75
    EOS
    -0.75
     frail
    -0.73
     respirator
    -0.72
     depre
    -0.72
     Resili
    -0.71
    POSITIVE LOGITS
     reflux
    3.13
     ref
    2.03
    ref
    2.02
    Ref
    1.76
     regurg
    1.54
     Ref
    1.30
    REF
    1.19
     terug
    1.16
    回
    1.13
     back
    1.12
    Activations Density 0.087%

    No Known Activations