© 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. 34591
    Prev
    Next
    INDEX
    Explanations

    cannabis treatments for conditions

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

    medical terminology related to treatments, conditions, and health research.

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

    The neuron is tuned to detect claims about medical cannabis (or marijuana) helping to manage health conditions.

    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
     freezer
    -0.71
     freezes
    -0.70
    ポーズ
    -0.69
    Abon
    -0.69
    知り
    -0.68
     AFP
    -0.68
     gén
    -0.68
     sniffing
    -0.67
     Mez
    -0.67
     plants
    -0.67
    POSITIVE LOGITS
     glaucoma
    0.90
    exit
    0.90
    Add
    0.89
     Epid
    0.87
     Throw
    0.84
    throw
    0.84
    ADD
    0.82
     Add
    0.81
     nausea
    0.81
     anorexia
    0.81
    Activations Density 0.023%

    No Known Activations