© 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. 33723
    Prev
    Next
    INDEX
    Explanations

    food safety and quality standards

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

    terms related to food safety, agriculture regulations, and government food agencies.

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

    The neuron strongly activates on uppercase acronyms, abbreviations, and other specialist proper-name tokens (e.g. “AF,” “SSA‐LER,” “LC-MS,” “Food Standards Agency,” etc.).

    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
    瓷
    -0.89
     vinaigrette
    -0.87
     estacionamento
    -0.83
     equipes
    -0.81
     stationnement
    -0.81
     bekommt
    -0.80
    诱
    -0.80
    接种
    -0.77
    Pizza
    -0.77
    ETRY
    -0.77
    POSITIVE LOGITS
     food
    1.87
     Food
    1.84
     inspection
    1.58
    Food
    1.52
     consumer
    1.51
     consumers
    1.47
     Codex
    1.46
     safety
    1.42
     quarantine
    1.38
     standards
    1.34
    Activations Density 0.052%

    No Known Activations