© 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. 84539
    Prev
    Next
    INDEX
    Explanations

    local food and farming

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

    content related to sustainable food systems, organic farming, and local agriculture.

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

    The neuron strongly activates on numeric and quantifying language—years, figures, percentages, counts—i.e. statistical or quantitative information in the text.

    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
     vino
    -1.02
    ဤ
    -0.98
     MediaPlayer
    -0.96
    coffee
    -0.94
     PROPERTY
    -0.93
    construction
    -0.91
    呓
    -0.91
    Ἰ
    -0.91
    Vertex
    -0.90
     Kelle
    -0.90
    POSITIVE LOGITS
     food
    2.16
     Food
    1.61
     local
    1.49
     Local
    1.42
     foods
    1.37
     farm
    1.36
    Food
    1.35
     eaters
    1.34
     Farm
    1.30
     eating
    1.25
    Activations Density 0.036%

    No Known Activations