© 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. 31761
    Prev
    Next
    INDEX
    Explanations

    beet and root vegetables

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

    names of root vegetables and related plant parts like beets, turnips, and sugar beets.

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

    The neuron activates on mentions of edible root vegetables (e.g. beet, horseradish, turnip, carrot, “root,” etc.) and related descriptors.

    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
    Orchid
    -0.89
     guacamole
    -0.88
     orchid
    -0.88
     hammock
    -0.87
     CIG
    -0.85
     McKinsey
    -0.82
     Rice
    -0.80
     omelette
    -0.79
     apricots
    -0.78
     Bananas
    -0.77
    POSITIVE LOGITS
     root
    1.29
     beet
    1.27
    root
    1.20
    roots
    1.20
     roots
    1.15
     beets
    1.05
     beetroot
    1.02
    根
    0.98
     Beet
    0.96
     Roots
    0.94
    Activations Density 0.010%

    No Known Activations