© 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. 116444
    Prev
    Next
    INDEX
    Explanations

    burger and hamburger

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

    The neuron activates on words referring to burgers and burger‐related 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
    チキン
    -0.86
     florist
    -0.83
     donuts
    -0.82
    デザート
    -0.79
     granola
    -0.79
    唐揚げ
    -0.77
     Guinée
    -0.75
    จีน
    -0.75
    gran
    -0.73
     noodle
    -0.73
    POSITIVE LOGITS
     burger
    2.78
     burgers
    2.59
    🍔
    2.31
     Burger
    2.17
     Burgers
    1.98
    Burger
    1.95
    burger
    1.94
     hamburger
    1.79
    burgers
    1.68
     hamburgers
    1.67
    Activations Density 0.023%

    No Known Activations