© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113807
    Prev
    Next
    INDEX
    Explanations

    soy and soybean

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

    mentions of soy, soybeans, or soy-related products in text.

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

    The neuron detects occurrences of “soy” (including compounds like “soybean,” “soy sauce,” 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_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
     Their
    -2.92
    ୌ
    -2.66
    代わり
    -2.64
    🡺
    -2.55
    ꠥ
    -2.47
     They
    -2.44
    ));
    -2.41
     famosas
    -2.39
    CHREIB
    -2.39
    𝘵
    -2.36
    POSITIVE LOGITS
    {
    4.34
    *
    3.00
    %
    2.77
    e
    2.72
    )
    2.70
    釭
    2.45
    (
    2.44
    k
    2.42
    2
    2.41
    the
    2.39
    Activations Density 0.002%

    No Known Activations