© 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. 117571
    Prev
    Next
    INDEX
    Explanations

    sulfur dioxide

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

    chemical compounds containing sulfur, especially sulfite and sulfate compounds.

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

    The neuron detects mentions of sulfur‐oxide anions, especially “sulfite”/“bisulfite” chemical terms.

    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
     Goed
    -0.79
     lekar
    -0.77
     Erdogan
    -0.77
     rechts
    -0.76
     lois
    -0.75
    Rotary
    -0.74
    }}}}
    -0.73
     alkoholu
    -0.73
    ISCO
    -0.73
    dane
    -0.71
    POSITIVE LOGITS
     SO
    1.43
     dioxide
    1.40
    SO
    1.24
     Dioxide
    0.96
     metab
    0.90
     gelesen
    0.77
     anhydride
    0.75
     सो
    0.73
     Metab
    0.71
     monitors
    0.70
    Activations Density 0.052%

    No Known Activations