© 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. 116786
    Prev
    Next
    INDEX
    Explanations

    peak oil and depletion

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

    technical content related to programming, data, or scientific documentation.

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

    The neuron strongly activates on technical, quantitative terms and phrases used in resource‐forecasting and depletion analyses (e.g. depletion, hydrocarbon, recoverable, peaks, production, estimates, forecasts).

    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
     Humidity
    -0.90
    Humidity
    -0.88
     microstructure
    -0.86
    humidity
    -0.84
     flott
    -0.83
    Holly
    -0.81
    loaf
    -0.81
     NLRB
    -0.81
     Renoir
    -0.80
    ierto
    -0.80
    POSITIVE LOGITS
     peak
    1.79
     Peak
    1.75
    peak
    1.61
     oil
    1.55
    Peak
    1.52
     peaking
    1.30
     peaked
    1.29
     energy
    1.25
     depletion
    1.23
     Oil
    1.20
    Activations Density 0.016%

    No Known Activations