© 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. 34-GEMMASCOPE-RES-131K
    7. 117281
    Prev
    Next
    INDEX
    Explanations

    legumes and dried beans

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

    food items and crops, especially legumes, grains, and plant-based proteins.

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

    This neuron detects mentions of legume‐derived foods and proteins—especially soybeans and related plant seed or nut sources.

    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
     Bree
    -0.79
    Myr
    -0.76
     halaman
    -0.75
    PrivateRoute
    -0.73
    宝
    -0.72
    ᵢ
    -0.71
    FORC
    -0.70
     ошибка
    -0.70
     icons
    -0.69
     Xen
    -0.69
    POSITIVE LOGITS
     soybeans
    1.13
     peas
    1.02
     bean
    0.99
     beans
    0.96
     pinto
    0.92
     lentils
    0.92
     pea
    0.90
     горо
    0.87
     cow
    0.86
     cracked
    0.86
    Activations Density 0.050%

    No Known Activations