© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 73331
    Prev
    Next
    INDEX
    Explanations

    environmental and advocacy terms

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

    terms related to environmental sustainability and green building practices.

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

    The neuron is tuned to pick out green‐building and sustainability–related terms—especially references to net-zero, energy- and water-efficiency, recycled materials, emissions reductions, and similar environmental performance metrics.

    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
    Дей
    -0.76
     сосу
    -0.76
    一言
    -0.76
    iasaan
    -0.73
     tutur
    -0.71
    matched
    -0.70
     puzzling
    -0.68
     academically
    -0.68
    cuad
    -0.67
    東南
    -0.67
    POSITIVE LOGITS
     embodied
    1.02
     credits
    0.89
    odied
    0.86
     McDonough
    0.83
     VOC
    0.81
    Ƭ
    0.79
    Quellen
    0.78
     materials
    0.77
     regional
    0.76
     Materials
    0.76
    Activations Density 0.017%

    No Known Activations