© 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. 59674
    Prev
    Next
    INDEX
    Explanations

    oxidative stress

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

    The neuron identifies "oxidative stress" in scientific medical contexts, particularly in studies about cellular damage.

    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_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
     Tonnen
    -2.70
    .”
    -2.47
    馐
    -2.45
    ).
    -2.30
    ’
    -2.25
     Schiffe
    -2.23
    ],
    -2.23
     Aufführung
    -2.19
     to
    -2.17
    allergenic
    -2.14
    POSITIVE LOGITS
    ︲
    2.78
    芣
    2.64
    咵
    2.59
    𓐍
    2.41
    ᠁
    2.38
    笮
    2.22
    艫
    2.17
    
    2.17
    Ꮏ
    2.13
     unravel
    2.06
    Activations Density 0.017%

    No Known Activations