© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110418
    Prev
    Next
    INDEX
    Explanations

    Brazilian poorly studied biodiversity

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

    content related to herbal medicine, remedies, and traditional plant-based treatments.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     Eggs
    -1.00
     psychologists
    -0.98
     psychology
    -0.98
     Phosphorus
    -0.97
     Maize
    -0.91
     Apples
    -0.86
     Fertilizer
    -0.86
     Lobster
    -0.85
     golfer
    -0.84
     Coconut
    -0.84
    POSITIVE LOGITS
     herbal
    2.69
     herb
    2.34
     herbs
    2.31
    Herbal
    2.14
     Herbal
    2.11
    herbal
    2.11
     plant
    1.91
     plants
    1.90
     medicinal
    1.83
    herb
    1.82
    Activations Density 0.155%

    No Known Activations