© 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. 91002
    Prev
    Next
    INDEX
    Explanations

    vegetarianism and veganism

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

    content related to veganism and vegetarianism.

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

    The neuron activates on terms and phrases related to veganism and vegetarianism.

    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
     golf
    -0.89
     cherries
    -0.83
    虾
    -0.83
    śnie
    -0.81
    uglify
    -0.79
     cinnamon
    -0.76
     raspberries
    -0.76
     chocolate
    -0.75
     strawberries
    -0.74
     Kammer
    -0.74
    POSITIVE LOGITS
     vegetarian
    3.78
     vegan
    3.52
     Vegan
    2.98
     vegetarians
    2.95
     Vegetarian
    2.91
    vegan
    2.75
    vegetarian
    2.75
    Vegan
    2.69
     vegans
    2.50
    Vegetarian
    2.38
    Activations Density 0.047%

    No Known Activations