© 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. 10-GEMMASCOPE-RES-131K
    7. 112881
    Prev
    Next
    INDEX
    Explanations

    nitro and nitrate compounds

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

    chemical compounds containing nitro groups and nitrates in scientific contexts.

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

    The neuron fires on chemical names and formulas that involve “nitro,” “nitrate,” “nitric oxide,” or related NOₓ species.

    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
    臯
    -2.09
    簠
    -1.88
    h
    -1.66
     ſie
    -1.63
    涐
    -1.61
    女性の
    -1.60
     sorrowful
    -1.58
     meagre
    -1.57
    這些
    -1.57
    </em>
    -1.56
    POSITIVE LOGITS
    .
    2.19
    ↵
    1.96
     the
    1.84
    」,
    1.78
     decorada
    1.71
     firmado
    1.70
    ⢕
    1.65
    硨
    1.64
     felicitación
    1.64
    とその
    1.63
    Activations Density 0.052%

    No Known Activations