© 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. 10-GEMMASCOPE-RES-131K
    4. 130630
    Prev
    Next
    INDEX
    Explanations

    oil and gas industry terms

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

    The neuron detects mentions of the oil‐and‐gas industry, especially the word “gas” (often in the phrase “oil and gas”) or closely related well-drilling terminology.

    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
    '
    -1.82
    (
    -1.65
    y
    -1.59
    \
    -1.49
     ''
    -1.46
     dlaczego
    -1.45
     iria
    -1.39
    =
    -1.39
    色々
    -1.38
     materiaal
    -1.38
    POSITIVE LOGITS
    </strong>
    2.25
     Stornier
    1.99
     gekenn
    1.69
     of
    1.60
     praises
    1.59
    
    1.56
     erwähnten
    1.54
    
    1.52
     stehenden
    1.50
     sogni
    1.47
    Activations Density 0.008%

    No Known Activations