© 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. 22-GEMMASCOPE-RES-131K
    7. 27270
    Prev
    Next
    INDEX
    Explanations

    types of beans, peas, or legumes

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

    The neuron detects mentions of plant‐based protein sources (legumes, beans, peas, pulses, soy, seeds, 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_22/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
    ,
    -1.28
    [
    -1.24
     новая
    -1.22
    ing
    -1.18
     brauche
    -1.17
     dachte
    -1.16
    レア
    -1.16
     he
    -1.15
    駐車
    -1.13
     dianteira
    -1.13
    POSITIVE LOGITS
     Kiedy
    1.44
    ֺ
    1.35
    hermoso
    1.31
     menyen
    1.30
     bluse
    1.29
    、
    1.29
     歯
    1.28
    婓
    1.28
     Aktivität
    1.27
    >//
    1.27
    Activations Density 0.012%

    No Known Activations