© 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. 107704
    Prev
    Next
    INDEX
    Explanations

    fluorescence emission spectra

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

    scientific terms related to light emission, particularly fluorescence, luminescence, and spectroscopy.

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

    The neuron strongly activates on technical terms related to fluorescence spectroscopy and emission measurements.

    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
    벌
    -0.80
    jär
    -0.80
     Kad
    -0.79
     fluorescence
    -0.77
    лізу
    -0.77
    τυ
    -0.76
    先生の
    -0.76
    DeleteMapping
    -0.74
    时期
    -0.72
    Fluorescence
    -0.72
    POSITIVE LOGITS
     spectra
    1.30
     measurements
    1.14
     efficiency
    1.03
     spectroscopy
    0.95
     spectrum
    0.88
     signal
    0.87
     coefficient
    0.87
     microscopy
    0.84
     measurement
    0.82
    spectra
    0.82
    Activations Density 0.153%

    No Known Activations