© 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. 102166
    Prev
    Next
    INDEX
    Explanations

    intravenous medical treatments

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

    The neuron detects the word "intravenous" and related medical/clinical terms like "stuffed", "transfusion", and "fluids" in medical and product 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_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
    en
    -3.31
    u
    -3.11
    er
    -3.11
    k
    -2.83
    x
    -2.44
    ar
    -2.41
    _
    -2.38
    f
    -2.31
    在我
    -2.30
    (
    -2.28
    POSITIVE LOGITS
    <bos>
    3.27
    丝毫
    2.83
     It
    2.48
    乆
    2.44
    偸
    2.36
    鹮
    2.28
     conhecida
    2.27
    欵
    2.27
    勦
    2.20
    ୌ
    2.19
    Activations Density 0.010%

    No Known Activations