© 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. 34-GEMMASCOPE-RES-131K
    7. 90647
    Prev
    Next
    INDEX
    Explanations

    seasonal vegetables

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

    This neuron detects mentions of specific vegetables or produce items.

    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
     Hamburger
    -0.88
     hamburger
    -0.78
     adobe
    -0.77
    Hamburger
    -0.77
    gatsby
    -0.73
    áló
    -0.73
    زمین
    -0.71
    urllib
    -0.71
    <0xE9>
    -0.70
    เนื้อ
    -0.69
    POSITIVE LOGITS
     peas
    1.70
     beans
    1.32
     green
    1.23
     Peas
    1.20
     frozen
    1.10
     pea
    1.08
    peas
    1.03
    frozen
    1.02
     snap
    1.01
    green
    0.96
    Activations Density 0.018%

    No Known Activations