© 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. 34-GEMMASCOPE-RES-131K
    7. 64229
    Prev
    Next
    INDEX
    Explanations

    super superoxide dismutase

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

    scientific terminology related to chemical compounds, particularly "superoxide" in chemical and biochemical contexts.

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

    The neuron responds to unusually long compound tokens split into subword pieces—e.g. multi‐part method or class names like “DeserializeObject” or biochemical terms like “superoxide” in “superoxide dismutase.”

    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
     soya
    -0.71
     Ernie
    -0.71
    trl
    -0.71
     Công
    -0.70
    超市
    -0.67
    IMUM
    -0.66
     leafs
    -0.66
     endoc
    -0.65
    Roz
    -0.64
    lysninger
    -0.64
    POSITIVE LOGITS
    bzero
    0.75
    زة
    0.71
     plenary
    0.69
     Wednesday
    0.69
    leville
    0.68
     Qing
    0.65
    delar
    0.65
     martes
    0.65
    ChildIndex
    0.64
     аль
    0.63
    Activations Density 0.055%

    No Known Activations