© 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. 57585
    Prev
    Next
    INDEX
    Explanations

    oxy- prefix compounds

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

    chemical compounds, especially those containing "oxy" prefix like oxytocin and oxycodone.

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

    This neuron activates on the “oxy” prefix in chemical and drug compound names.

    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
    亖
    -3.02
    乄
    -2.86
    伈
    -2.86
    箧
    -2.72
    啬
    -2.66
    乆
    -2.63
    を使用した
    -2.61
    ⩤
    -2.61
    
    -2.55
    哢
    -2.55
    POSITIVE LOGITS
     {
    2.94
     July
    2.58
    "
    2.53
     September
    2.53
     November
    2.52
     unrelenting
    2.39
     February
    2.31
    糞
    2.31
    Fifteen
    2.31
     October
    2.27
    Activations Density 0.013%

    No Known Activations