© 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. 22-GEMMASCOPE-RES-131K
    7. 33124
    Prev
    Next
    INDEX
    Explanations

    nitric oxide and nitrate

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

    chemical compounds related to nitrogen oxides, particularly nitric oxide and nitrates, in scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron selectively activates on mentions of nitric oxide (and closely related nitrogen oxide terms or abbreviations).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    簠
    -2.64
    M
    -2.27
    Зно
    -2.27
    …’
    -2.25
     incluidas
    -2.23
     verlieren
    -2.22
    每一个
    -2.19
    ,’
    -2.16
    荩
    -2.16
     требуется
    -2.11
    POSITIVE LOGITS
    .
    2.77
    硨
    2.08
    ization
    2.03
     '
    2.02
    ЛОВ
    1.91
    ☑
    1.90
     rękaw
    1.85
    鴆
    1.84
    ла
    1.83
     expedited
    1.82
    Activations Density 0.024%

    No Known Activations