© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44216
    Prev
    Next
    INDEX
    Explanations

    well operations

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

    The neuron fires on technical mentions of “well”-related terms (e.g. gas well, horizontal well, bore, borehole) in an oil-and-gas drilling context.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    皲
    -2.13
    撺
    -2.05
     urgente
    -2.02
    ㌧
    -2.00
    
    -1.96
     mesmas
    -1.94
    尐
    -1.89
    اما
    -1.88
     zdję
    -1.84
    真的好
    -1.84
    POSITIVE LOGITS
    s
    2.22
     staunch
    2.06
     When
    2.02
     With
    1.94
     What
    1.93
     sebab
    1.91
     misguided
    1.88
     This
    1.84
     éditoriale
    1.83
     légale
    1.79
    Activations Density 0.017%

    No Known Activations