© 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. 33088
    Prev
    Next
    INDEX
    Explanations

    garden, farm, cultivation, fruits, spices

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

    agricultural and food-related terminology, particularly crop names and farming activities.

    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
     wheat
    -0.87
     grain
    -0.81
    grain
    -0.73
    Prairie
    -0.70
    Grain
    -0.69
     AppColors
    -0.69
     sourdough
    -0.68
     barley
    -0.68
    防守
    -0.68
     Grain
    -0.67
    POSITIVE LOGITS
     pepper
    1.00
     dragon
    0.94
     fertig
    0.94
    dragon
    0.87
     turmeric
    0.86
     ginger
    0.83
     Buckingham
    0.83
    ITECH
    0.83
     Tissue
    0.82
    pepper
    0.82
    Activations Density 0.013%

    No Known Activations