© 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. 10-GEMMASCOPE-RES-131K
    7. 105027
    Prev
    Next
    INDEX
    Explanations

    reactive oxygen species

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

    This neuron detects scientific terms related to oxidative stress and reactive oxygen species (ROS) in biochemical and medical research contexts.

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

    The neuron activates on mentions of reactive oxygen species and related oxidative stress terminology.

    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
    in
    -2.16
    u
    -1.70
    at
    -1.51
    don
    -1.47
     facendo
    -1.46
    by
    -1.45
    ou
    -1.42
    on
    -1.41
    ;-
    -1.36
    ap
    -1.35
    POSITIVE LOGITS
    }
    1.70
     ПОД
    1.52
    volles
    1.46
     sabiduría
    1.44
     particularmente
    1.42
    Hose
    1.41
    ☎️
    1.40
    ▾
    1.38
     vendidos
    1.38
     partes
    1.35
    Activations Density 0.130%

    No Known Activations