© 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. 101049
    Prev
    Next
    INDEX
    Explanations

    vegetable consumption

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

    references to vegetables or vegetable-related terms in food contexts.

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

    The neuron activates on words referring to vegetables or related plant‐based produce.

    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
     花卉
    -1.77
     perde
    -1.62
     interi
    -1.57
    şört
    -1.57
     gata
    -1.54
    atás
    -1.54
     gord
    -1.54
     anse
    -1.53
     paradiso
    -1.52
     dekoratif
    -1.52
    POSITIVE LOGITS
     Когда
    2.14
     When
    1.91
    худ
    1.79
     """
    1.76
     "-
    1.71
     aseguran
    1.63
     another
    1.62
    橦
    1.58
    </i>
    1.54
    睨
    1.53
    Activations Density 0.013%

    No Known Activations