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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86474
    Prev
    Next
    INDEX
    Explanations

    seed planting and female pigs

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

    The neuron identifies variants of the word "sow" (sowing, sowed, sows) and related agricultural/seed planting concepts.

    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
    W
    -2.67
    ”،
    -2.36
    ي
    -2.33
    
    -2.27
    U
    -2.27
    ・・・。
    -2.22
    従
    -2.22
    .
    -2.17
    ');
    -2.17
     is
    -2.17
    POSITIVE LOGITS
     ſay
    2.64
    ܆
    2.28
    厹
    2.14
    獓
    2.14
     atualmente
    2.13
    很赞
    2.11
     enfati
    2.09
    퐴
    2.03
    沵
    2.02
    之际
    2.00
    Activations Density 0.002%

    No Known Activations