© 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. 50432
    Prev
    Next
    INDEX
    Explanations

    spectral wavelength and emission regions

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

    scientific discussions about light wavelengths and spectral characteristics in technical documents.

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

    The neuron detects mentions of electromagnetic spectrum parameters—especially numeric wavelengths, spectral‐region names, and related light/radiation terms.

    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
     regulador
    -0.92
     sleeping
    -0.90
    oneta
    -0.88
     amplificador
    -0.86
     pessoais
    -0.85
    HEAST
    -0.84
     mensajes
    -0.83
    bakter
    -0.82
     denuncias
    -0.81
    íně
    -0.81
    POSITIVE LOGITS
     spectral
    2.70
     wavelength
    2.56
     spectrum
    2.45
     wavelengths
    2.38
     spectra
    2.27
    wavelength
    2.06
     Spectral
    2.03
     спек
    1.99
    spectral
    1.94
    Spectral
    1.74
    Activations Density 0.162%

    No Known Activations