© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32651
    Prev
    Next
    INDEX
    Explanations

    pharmacies and health stores

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

    pharmacy and drugstore names or related retail terminology.

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

    The neuron fires on references to pharmacies and pharmacy‐related entities—e.g. pharmaceutical chains (CVS, Walgreens, Shoppers Drug Mart, Rite Aid), the words “pharmacy,” “pharmacist,” “pharmacies,” and “drug.”

    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
    مرار
    -0.83
    ushka
    -0.81
     Nordstrom
    -0.79
     statewide
    -0.78
    ليج
    -0.78
    数学
    -0.77
    Nichts
    -0.75
     Sizing
    -0.75
     dealership
    -0.74
    urra
    -0.74
    POSITIVE LOGITS
     CVS
    1.02
     Minute
    0.94
     convenient
    0.89
     Beauty
    0.86
    いじ
    0.86
     Red
    0.85
     beauty
    0.85
     store
    0.84
     greeting
    0.82
     Convenient
    0.82
    Activations Density 0.007%

    No Known Activations