© 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. 34-GEMMASCOPE-RES-131K
    4. 4249
    Prev
    Next
    INDEX
    Explanations

    substance use and addiction research

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

    citations and references in academic papers about substance use, addiction, and health research.

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

    The neuron detects bibliographic reference tokens—especially numbers and punctuation used in citations (years, volume/issue numbers, page numbers, DOIs, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    AGEMENT
    -0.73
    airbnb
    -0.72
    Ϋ
    -0.70
    $.}
    -0.69
    🤽
    -0.69
    とある
    -0.68
    ILON
    -0.67
    僑
    -0.67
    ayashi
    -0.66
     tabung
    -0.66
    POSITIVE LOGITS
     Addiction
    2.02
    Addiction
    1.86
     addiction
    1.84
     addicts
    1.67
     Substance
    1.65
     Alcohol
    1.62
     addict
    1.59
     Drug
    1.58
    Substance
    1.54
     addicted
    1.52
    Activations Density 0.070%

    No Known Activations