© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92337
    Prev
    Next
    INDEX
    Explanations

    food and eating

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

    references to food consumption, preparation, or digestion.

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

    The neuron fires on positive evaluative adjectives expressing praise or favorable qualities (e.g. good, tasty, delicious, aesthetically pleasing).

    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
    ध्यम
    -0.85
     contient
    -0.82
     држа
    -0.81
    ágos
    -0.79
    幽默
    -0.78
    讥
    -0.75
    ribu
    -0.75
    Consumption
    -0.74
     سكانية
    -0.74
    škai
    -0.73
    POSITIVE LOGITS
     food
    5.59
    food
    3.28
     foods
    3.19
     Food
    2.89
     FOOD
    2.80
    Food
    2.77
     cibo
    2.75
    FOOD
    2.55
     nourriture
    2.47
     meals
    2.44
    Activations Density 0.051%

    No Known Activations