© 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. 45208
    Prev
    Next
    INDEX
    Explanations

    carbon dioxide

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

    chemical formulas and references to carbon dioxide in scientific texts.

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

    The neuron activates on occurrences of the word “dioxide,” especially in chemical or environmental contexts.

    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
    ed
    -3.09
    re
    -3.02
    N
    -2.97
    en
    -2.95
    M
    -2.91
    ie
    -2.73
    end
    -2.66
    l
    -2.63
    O
    -2.59
    </b>
    -2.58
    POSITIVE LOGITS
    灩
    2.55
    </h3>
    2.39
    趼
    2.33
    觏
    2.22
     decorada
    2.19
    
    2.17
     decorado
    2.17
    '#
    2.08
    焄
    2.05
    Penguin
    2.03
    Activations Density 0.011%

    No Known Activations