© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43037
    Prev
    Next
    INDEX
    Explanations

    Schiff bases and aldehydes

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

    This neuron detects chemical compounds and functional groups in scientific literature, particularly focusing on aldehydes and related organic chemistry terms.

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

    This neuron responds to mentions of organic‐chemistry entities and processes, e.g. names of compounds (aldehydes, isoquinolines, azolidines) and reaction types (carbonyl cyclization, coupling reactions).

    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
     monstrous
    -1.80
     predominantly
    -1.76
    
    -1.75
    菒
    -1.71
     startling
    -1.71
    鼱
    -1.68
    秶
    -1.67
     núm
    -1.66
    ౭
    -1.66
    蠖
    -1.65
    POSITIVE LOGITS
     ALWAYS
    1.57
     start
    1.55
     EVERY
    1.53
     }
    1.52
    водов
    1.41
     \&
    1.41
    1
    1.38
     &
    1.38
    接近
    1.38
    нули
    1.34
    Activations Density 0.078%

    No Known Activations