© 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. 34-GEMMASCOPE-RES-131K
    7. 64047
    Prev
    Next
    INDEX
    Explanations

    oil blocks exploration acreage

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

    The main thing this neuron does is detect references to the oil and gas industry—terms like oil, drilling, exploration, contracts, companies, etc.

    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
    lanco
    -0.75
    Synopsis
    -0.72
    これも
    -0.71
    ineno
    -0.71
    centralwidget
    -0.71
    setzungen
    -0.66
    hesus
    -0.66
     facility
    -0.66
     جلوگیری
    -0.66
     parah
    -0.66
    POSITIVE LOGITS
     blocks
    1.36
     acreage
    1.26
     Blocks
    1.23
     exploration
    1.22
    blocks
    1.20
     Exploration
    1.09
    Blocks
    1.08
     BLOCK
    1.07
     Block
    1.05
     explorer
    1.05
    Activations Density 0.021%

    No Known Activations