© 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. 59203
    Prev
    Next
    INDEX
    Explanations

    physiological and pathophysiological states

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

    The neuron detects the word "physiological" and related terms like "physio", "physiologic", and "pathology" in scientific or medical contexts.

    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
     Divisions
    -0.91
    骜
    -0.90
     scienza
    -0.89
     چیه
    -0.89
     千葉
    -0.88
     ufficio
    -0.87
     viata
    -0.86
    nisses
    -0.84
    iczny
    -0.84
    راد
    -0.84
    POSITIVE LOGITS
     and
    0.82
     saline
    0.81
    人类
    0.81
     SG
    0.80
    做
    0.79
    新闻
    0.79
    pstead
    0.77
    showMessage
    0.77
     辣
    0.77
    意义
    0.75
    Activations Density 0.024%

    No Known Activations