© 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. 10-GEMMASCOPE-RES-131K
    4. 9181
    Prev
    Next
    INDEX
    Explanations

    stent and related medical terms

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

    medical terms related to stents or stenting procedures in blood vessels and urological contexts.

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

    The neuron spotlights occurrences of the word “stent” (and its morphological variants like “stenting” or “stents”).

    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
    derdag
    -2.52
    姈
    -2.41
    可能な
    -2.36
    慤
    -2.33
     comienzo
    -2.30
    )\
    -2.30
     Enlightenment
    -2.27
    媖
    -2.23
    。
    
    -2.23
    ها
    -2.23
    POSITIVE LOGITS
    \
    2.42
    2.41
    0
    2.39
    '
    2.31
    ates
    2.28
     
    2.27
    いら
    2.13
    .'
    2.11
     We
    2.06
    ίες
    2.03
    Activations Density 0.022%

    No Known Activations