© 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. 34-GEMMASCOPE-RES-131K
    7. 87266
    Prev
    Next
    INDEX
    Explanations

    agriculture, horticulture, viticulture, apiculture

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

    terminology related to agriculture and agricultural fields (like viticulture, apiculture, horticulture).

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

    The neuron is triggered by domain-specific agricultural and related scientific roots (e.g. agri-, apic-, silvic-, vitic-, bee-).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    NVIDIA
    -0.79
    奂
    -0.78
    mäß
    -0.76
    fordable
    -0.73
     [{\
    -0.73
    ffel
    -0.72
    wój
    -0.72
    
    -0.71
     góry
    -0.71
    寤
    -0.70
    POSITIVE LOGITS
    culture
    2.02
     culture
    2.00
     cultural
    1.80
     Culture
    1.74
    Culture
    1.69
    cultural
    1.63
    文化
    1.52
     Cultural
    1.50
     cultura
    1.44
    kultur
    1.43
    Activations Density 0.051%

    No Known Activations