© 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. 9734
    Prev
    Next
    INDEX
    Explanations

    substance use or abuse

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

    The neuron detects the word "substance" particularly when it appears in contexts related to abuse, use disorders, or pharmaceuticals.

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

    The neuron strongly activates on occurrences of the token “substance,” especially in phrases like “substance use” or “substance abuse.”

    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
    毉
    -3.25
    栳
    -3.14
    鬭
    -2.77
     boneka
    -2.69
     Tonnen
    -2.66
    嵛
    -2.66
    镦
    -2.61
    厛
    -2.61
    élène
    -2.59
    蛲
    -2.56
    POSITIVE LOGITS
    ↵↵
    3.77
     And
    2.88
     alleviate
    2.50
     บาง
    2.50
     \&
    2.41
    …？
    2.38
     communicate
    2.36
     избежать
    2.34
     uncover
    2.33
     enforce
    2.28
    Activations Density 0.005%

    No Known Activations