© 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. 12733
    Prev
    Next
    INDEX
    Explanations

    hospitals, health, care, medication, surgeons

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

    terms related to medical facilities, healthcare, and hospitals.

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

    The main thing this neuron does is detect medical and healthcare–related terms (diseases, treatments, hospitals, health services, 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
     its
    -1.28
    洗手
    -1.17
     may
    -1.16
    および
    -1.16
     which
    -1.15
     If
    -1.15
     after
    -1.09
     Both
    -1.09
    Ծանոթ
    -1.09
    </h1>
    -1.08
    POSITIVE LOGITS
    aians
    1.30
     circon
    1.29
    behandlung
    1.23
    眎
    1.22
     家用
    1.22
     tratamientos
    1.20
    ňuje
    1.20
    Formazione
    1.17
    especially
    1.16
     любое
    1.16
    Activations Density 0.100%

    No Known Activations