© 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. 70522
    Prev
    Next
    INDEX
    Explanations

    opioid abuse, overdose, dependence

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

    The neuron detects terms related to opioids, particularly the words "opioid" and "opioids" in medical or research 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
    es
    -2.97
    at
    -2.78
     scrutin
    -2.73
    in
    -2.63
    在自己
    -2.48
    实力
    -2.34
     "
    -2.31
     them
    -2.28
    NESSEE
    -2.25
    随即
    -2.23
    POSITIVE LOGITS
     إنها
    2.44
    เพื่อ
    2.39
    เพราะ
    2.33
    鉭
    2.23
     当
    2.23
    arraycopy
    2.20
    низ
    2.20
     和
    2.14
     смотреть
    2.11
     设置
    2.08
    Activations Density 0.005%

    No Known Activations