© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84360
    Prev
    Next
    INDEX
    Explanations

    seeds and seed products

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

    botanical or plant-derived seeds, particularly sesame, flax, and other nutritional seeds.

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

    The neuron strongly activates on subword pieces that together spell “sesame,” so it detects mentions of “sesame.”

    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
     sugarcane
    -0.82
    velocityX
    -0.81
    יצוב
    -0.81
     微信
    -0.81
     Frases
    -0.80
     carrots
    -0.79
    οντας
    -0.78
     turmeric
    -0.77
     lastName
    -0.76
    inent
    -0.76
    POSITIVE LOGITS
     seeds
    2.83
     seed
    2.33
     Seeds
    2.19
    seeds
    2.14
    Seeds
    1.91
    seed
    1.84
     Seed
    1.74
     semillas
    1.72
    Seed
    1.60
    SEED
    1.47
    Activations Density 0.011%

    No Known Activations