© 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. 23845
    Prev
    Next
    INDEX
    Explanations

    nitrogen oxides

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

    chemical compounds and emissions-related terms, particularly oxides like nitric oxide, carbon monoxide, and sulfur dioxide.

    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
     zama
    -0.77
    gert
    -0.73
    zeczytaj
    -0.73
     села
    -0.72
     Stel
    -0.72
    ัว
    -0.72
     atacado
    -0.71
    pF
    -0.71
    Presidente
    -0.70
    お昼
    -0.70
    POSITIVE LOGITS
     NOx
    1.98
     nitrogen
    1.73
     NO
    1.69
     oxides
    1.60
    NO
    1.55
    NOX
    1.44
     nitric
    1.38
     Nitrogen
    1.37
     SO
    1.34
     nitrous
    1.30
    Activations Density 0.044%

    No Known Activations