© 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. 83951
    Prev
    Next
    INDEX
    Explanations

    offshore federal lease Arctic

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

    The neuron fires strongly on the specialized vocabulary of official offshore oil and gas leasing announcements.

    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
     Modesto
    -0.77
     Substan
    -0.75
     Lalu
    -0.73
     kolem
    -0.73
     Urbano
    -0.72
     STANFORD
    -0.72
     nepř
    -0.70
     Embedding
    -0.69
     urbano
    -0.69
     prairie
    -0.69
    POSITIVE LOGITS
     offshore
    1.79
     Offshore
    1.34
     OCS
    1.19
     federal
    1.16
    Offshore
    1.06
     Lease
    1.04
     leasing
    1.02
     Outer
    1.02
     off
    0.98
     Federal
    0.96
    Activations Density 0.043%

    No Known Activations