© 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. 10-GEMMASCOPE-RES-131K
    7. 59868
    Prev
    Next
    INDEX
    Explanations

    soybean products

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

    words related to soy and soybean products.

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

    The neuron fires on mentions of soy and its close variants (e.g. soy, soya, soybean).

    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
    ulipas
    -1.61
     They
    -1.59
     calça
    -1.55
    餍
    -1.50
    کیف
    -1.45
     蘭
    -1.45
    چنین
    -1.41
    镡
    -1.41
    不錯
    -1.41
    bulaire
    -1.40
    POSITIVE LOGITS
    with
    1.70
    ,”
    1.48
    緜
    1.47
    2
    1.46
        
    1.38
    ፔ
    1.37
    」、
    1.34
     другим
    1.34
    ecycle
    1.34
    for
    1.34
    Activations Density 0.016%

    No Known Activations