© 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. 22-GEMMASCOPE-RES-131K
    7. 38209
    Prev
    Next
    INDEX
    Explanations

    agriculture and agricultural topics

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

    words related to agriculture and agricultural contexts.

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

    The neuron detects mentions of agriculture or its close variants (e.g., “agriculture,” “agricultural”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ’
    -2.64
    俨
    -2.45
    ホント
    -2.41
    新た
    -2.39
     mangled
    -2.36
    满是
    -2.36
    イイ
    -2.34
    樒
    -2.33
    慢慢的
    -2.27
    で大
    -2.27
    POSITIVE LOGITS
    .
    3.33
    委員會
    2.22
     from
    2.05
     mayoría
    2.02
    墳
    2.00
    >
    2.00
    
    2.00
    ?”
    1.98
    旅館
    1.98
    渲
    1.95
    Activations Density 0.014%

    No Known Activations