© 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. 10-GEMMASCOPE-RES-131K
    7. 119766
    Prev
    Next
    INDEX
    Explanations

    farming and farmers

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

    references to farming, agriculture, and people who work the land.

    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_10/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
    UGHS
    -1.73
    喜歡的
    -1.51
    お値段
    -1.48
     Objec
    -1.47
    './
    -1.44
    脑子
    -1.43
    土曜
    -1.42
    お客
    -1.41
    のご
    -1.41
    
    -1.41
    POSITIVE LOGITS
        
    1.95
    回避
    1.62
     “
    1.62
     not
    1.58
    五年
    1.57
    OUR
    1.55
     If
    1.55
    二年
    1.54
    ve
    1.52
     last
    1.52
    Activations Density 0.067%

    No Known Activations