© 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. 74511
    Prev
    Next
    INDEX
    Explanations

    agriculture

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

    the word "agriculture" and related agricultural terms.

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

    The neuron activates on mentions of “agriculture” (and its direct derivatives) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    樒
    -2.97
    好吃的
    -2.73
    甃
    -2.63
    ет
    -2.47
     wth
    -2.44
     עם
    -2.30
    ꜆
    -2.28
    '
    -2.23
    気付
    -2.23
    デュー
    -2.23
    POSITIVE LOGITS
    .
    4.09
    ?”
    2.50
    ︲
    2.48
    蠓
    2.47
     kurzen
    2.44
    狆
    2.42
    vantaged
    2.39
    ”]
    2.33
     Verbesserung
    2.30
     häufigsten
    2.30
    Activations Density 0.006%

    No Known Activations