© 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. 89805
    Prev
    Next
    INDEX
    Explanations

    enantioselective chiral synthesis

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

    This neuron detects words and concepts related to stereochemistry, particularly focusing on chiral compounds, enantiomers, and stereoselective reactions.

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

    The neuron detects mentions of molecular stereochemistry, especially terms related to chirality and enantiomeric configurations.

    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
    ってみた
    -0.79
    藷
    -0.79
     säkert
    -0.79
     Paleo
    -0.77
     consenting
    -0.77
    祝い
    -0.75
    詡
    -0.75
     Betten
    -0.73
    bezpe
    -0.73
     استنادى
    -0.73
    POSITIVE LOGITS
     pockets
    0.85
     discrimination
    0.82
     Opposite
    0.81
     asymmetric
    0.79
     Shropshire
    0.76
    zentrum
    0.74
     AFP
    0.73
     Rue
    0.70
     форме
    0.70
     alphabet
    0.70
    Activations Density 0.096%

    No Known Activations