© 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. 98414
    Prev
    Next
    INDEX
    Explanations

    ketchup, tomato, Heinz

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

    The neuron fires on names of condiments or sauce‐type food items.

    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
     partisan
    -0.79
    óbal
    -0.79
    popcorn
    -0.75
     skimmed
    -0.73
     eingesetzt
    -0.73
     Kamala
    -0.71
    nissan
    -0.71
     ROH
    -0.70
     fodder
    -0.69
    Shiro
    -0.68
    POSITIVE LOGITS
     ketchup
    2.19
     Heinz
    1.35
    etchup
    1.25
     tomato
    1.25
     sauce
    1.17
     Tomato
    1.12
    番茄
    1.08
    Heinz
    1.02
    Tomato
    0.90
     Sauce
    0.90
    Activations Density 0.029%

    No Known Activations