© 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. 34-GEMMASCOPE-RES-131K
    7. 59241
    Prev
    Next
    INDEX
    Explanations

    CO2 laser and concentration

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

    chemical references to CO2 (carbon dioxide) in scientific texts.

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

    The neuron activates on occurrences of the chemical formula for carbon dioxide (CO₂).

    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
     كيل
    -0.86
    明日は
    -0.84
     menyediakan
    -0.82
    pezif
    -0.82
     mengadakan
    -0.81
    After
    -0.81
    急に
    -0.79
     menengah
    -0.79
    に住
    -0.79
    anius
    -0.78
    POSITIVE LOGITS
     gas
    1.20
    uitable
    0.84
     газ
    0.82
    ագրություն
    0.82
    griffen
    0.82
    aaaaa
    0.80
     '))
    0.78
    干嘛
    0.78
    pip
    0.77
     Gas
    0.77
    Activations Density 0.057%

    No Known Activations