© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78320
    Prev
    Next
    INDEX
    Explanations

    fresh produce and shopping

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

    The neuron fires strongly on mentions of markets (e.g. the word “market” or its variants in market names).

    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
     manufacturing
    -1.14
    manufacturing
    -1.04
    Manufacturing
    -1.01
     Manufacturing
    -0.97
     MANUFACTURING
    -0.88
    manufact
    -0.88
     Raff
    -0.84
    🍕
    -0.80
     manufacture
    -0.79
     Budi
    -0.78
    POSITIVE LOGITS
     fresh
    1.97
     produce
    1.70
    fresh
    1.57
     freshness
    1.51
    Fresh
    1.45
     vegetables
    1.43
     fruits
    1.37
    Produce
    1.34
    produce
    1.33
     Produce
    1.30
    Activations Density 0.028%

    No Known Activations