© 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. 117270
    Prev
    Next
    INDEX
    Explanations

    meals, dishes, and cuisine

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

    The neuron strongly activates for mentions of food, drink, menus, and other dining-related offerings.

    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
     because
    -1.16
     berichtet
    -1.05
     needed
    -1.03
     then
    -1.02
     today
    -1.02
     Bürgermeister
    -0.99
     fisuras
    -0.98
    市的
    -0.98
     hochwer
    -0.98
     when
    -0.98
    POSITIVE LOGITS
     served
    1.71
    served
    1.48
     prepared
    1.30
    Served
    1.14
     varier
    1.09
    prepared
    1.07
     سرو
    1.04
     Served
    1.02
    itahu
    1.02
    hanced
    1.00
    Activations Density 0.019%

    No Known Activations