© 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. 38143
    Prev
    Next
    INDEX
    Explanations

    fossil fuel and fossils

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

    terms related to fossil fuels and non-renewable energy sources.

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

    This neuron detects mentions of the term “fossil fuel.”

    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
    Gemeinsame
    -0.80
    一個人
    -0.80
    꽉
    -0.79
     tory
    -0.77
    詭
    -0.77
     obtu
    -0.77
     electrica
    -0.76
     zve
    -0.76
    uelve
    -0.76
    聽到
    -0.76
    POSITIVE LOGITS
     fuel
    1.70
     fuels
    1.59
    fuel
    1.37
    Fuel
    1.30
     Fuels
    1.29
    fuels
    1.23
     Fuel
    1.23
    燃料
    1.09
     records
    0.93
     Fools
    0.92
    Activations Density 0.014%

    No Known Activations