© 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. 103646
    Prev
    Next
    INDEX
    Explanations

    tracheal or tracheostomy

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

    medical terms related to the trachea and respiratory system.

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

    This neuron activates on occurrences of the substring “trache” (as in “tracheal,” “tracheostomy,” 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_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
    osa
    -0.79
     chiều
    -0.75
     Xian
    -0.73
     posky
    -0.73
    inu
    -0.71
    كتوبر
    -0.71
    λισ
    -0.70
    ")))
    -0.68
    pey
    -0.68
    Fuentes
    -0.68
    POSITIVE LOGITS
     terbukti
    0.68
    parseFrom
    0.66
    成分
    0.65
    路由
    0.65
     College
    0.65
    pollo
    0.63
     agree
    0.63
    ложений
    0.63
     Russland
    0.62
     Hinter
    0.61
    Activations Density 0.057%

    No Known Activations