© 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. 75486
    Prev
    Next
    INDEX
    Explanations

    NMR spectroscopy

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

    scientific spectroscopy techniques like NMR and their associated numerical data.

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

    This neuron detects numeric tokens or digit‐containing sequences—especially measurements, counts, and spectroscopy parameters—in scientific text.

    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
     uszkod
    -0.79
     tisíc
    -0.77
    äter
    -0.76
     svolge
    -0.74
     poš
    -0.74
     Mathem
    -0.70
     aikana
    -0.69
    🪁
    -0.69
     ká
    -0.68
     ricorda
    -0.68
    POSITIVE LOGITS
     NMR
    2.14
    NMR
    1.90
     ${
    1.72
     proton
    1.66
     Proton
    1.54
     Nuclear
    1.42
    Proton
    1.39
     nuclear
    1.35
    Nuclear
    1.34
    ${
    1.31
    Activations Density 0.076%

    No Known Activations