© 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. 90168
    Prev
    Next
    INDEX
    Explanations

    fuel, coal, and oil

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

    references to fuel sources, particularly coal, oil, and wood burning.

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

    The neuron chiefly picks up technical, fuel-and combustion-related terms and quantities—e.g. mentions of coal, gas, fuel/oil, burning, emissions and their numeric specifications.

    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
    favorited
    -0.88
    دکتر
    -0.77
     dair
    -0.76
    گي
    -0.75
    則是
    -0.74
    Reak
    -0.73
    祉
    -0.73
     Shasta
    -0.72
    Gratis
    -0.72
    ilà
    -0.72
    POSITIVE LOGITS
     fuel
    2.30
     coal
    2.16
     oil
    1.89
    fuel
    1.79
     boiler
    1.77
    Fuel
    1.70
     Fuel
    1.66
     Coal
    1.64
     firing
    1.63
    coal
    1.59
    Activations Density 0.028%

    No Known Activations