© 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. 22337
    Prev
    Next
    INDEX
    Explanations

    free radicals

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

    This neuron identifies the chemistry term "free radicals" in scientific text.

    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
     You
    -2.00
    ՚
    -1.75
     hız
    -1.73
    龛
    -1.69
    졍
    -1.66
    approximate
    -1.65
     childish
    -1.64
    …]
    -1.64
    旸
    -1.62
     ยัง
    -1.60
    POSITIVE LOGITS
    𖡼
    2.13
    於是
    2.00
    罍
    1.93
    
    1.80
    lahir
    1.78
    たち
    1.78
     our
    1.78
    ኧ
    1.76
    ＼(^
    1.76
     хотели
    1.71
    Activations Density 0.016%

    No Known Activations