© 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. 83633
    Prev
    Next
    INDEX
    Explanations

    methane capture and flaring

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

    references to methane or natural gas in scientific or technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     splashes
    -0.91
     HST
    -0.79
     Deepak
    -0.76
    ♙
    -0.76
     შ
    -0.75
    лас
    -0.75
    سرائيلي
    -0.75
     aload
    -0.74
    жаться
    -0.74
     mengangkat
    -0.72
    POSITIVE LOGITS
     capture
    1.37
     flare
    1.23
     flares
    1.16
     flared
    1.16
     Capture
    1.12
     capturing
    1.12
     methane
    1.07
     flaring
    1.07
     Capt
    1.05
    Capture
    1.04
    Activations Density 0.010%

    No Known Activations