© 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. 34-GEMMASCOPE-RES-131K
    7. 1778
    Prev
    Next
    INDEX
    Explanations

    synthesis and characterization of compounds

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

    scientific and technical language related to chemistry and materials science.

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

    This neuron detects uppercase section titles or headings—especially multiword uppercase phrases common in chemistry paper titles (e.g. “CLUSTER COMPOUNDS,” “COORDINATION COMPOUNDS”).

    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
    繳
    -0.75
    bory
    -0.74
    -|
    -0.72
     Amu
    -0.72
     aliqu
    -0.70
     Autonomous
    -0.68
     iodide
    -0.68
     componentes
    -0.68
    ưởng
    -0.68
     trực
    -0.67
    POSITIVE LOGITS
     reactions
    1.02
     studies
    0.95
    DETAILED
    0.88
     transformations
    0.86
     fontos
    0.85
    其妙
    0.84
     photo
    0.84
     reactivity
    0.84
     behavior
    0.84
     important
    0.84
    Activations Density 0.207%

    No Known Activations