© 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. 34-GEMMASCOPE-RES-131K
    7. 37893
    Prev
    Next
    INDEX
    Explanations

    recreational medical cannabis

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

    This neuron identifies content related to marijuana legalization, cannabis use, and medical/recreational marijuana policy.

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

    This neuron is a “cannabis topic” detector—it strongly activates on tokens naming or closely associated with marijuana (e.g. “cannabis,” “medical,” “recreational,” “marijuana,” place‐and‐use contexts).

    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
     erhöht
    -0.81
    द्र
    -0.81
    astery
    -0.75
    íram
    -0.75
    ター
    -0.74
     września
    -0.72
     estrenar
    -0.71
     diplomats
    -0.71
     unterstützt
    -0.70
     infancia
    -0.70
    POSITIVE LOGITS
     recreational
    2.48
     Recreational
    1.87
    Recre
    1.74
     medical
    1.73
     medicinal
    1.58
     adult
    1.45
     recreation
    1.42
     Medical
    1.40
    medical
    1.37
     RECRE
    1.27
    Activations Density 0.038%

    No Known Activations