© 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. 10-GEMMASCOPE-RES-131K
    7. 74031
    Prev
    Next
    INDEX
    Explanations

    vanilla and flavorings

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

    This neuron detects food flavoring-related terms, such as "flavoring," "flavors," "vanilla," and "tartrazine."

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     When
    -1.49
     nazionali
    -1.44
     under
    -1.44
     through
    -1.37
    inição
    -1.34
     enhancing
    -1.34
     misguided
    -1.34
    when
    -1.33
     Creating
    -1.32
    ၀
    -1.32
    POSITIVE LOGITS
    腘
    1.48
     نقطة
    1.41
     tornillos
    1.34
     și
    1.32
     identif
    1.30
    尨
    1.30
    に入れ
    1.30
     desierto
    1.27
    淚
    1.27
     取り付け
    1.27
    Activations Density 0.014%

    No Known Activations