© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33582
    Prev
    Next
    INDEX
    Explanations

    electromagnetic spectrum and visible light

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

    The neuron detects mentions of the electromagnetic spectrum and related wavelength or frequency ranges.

    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
    ativit
    -0.70
    rollo
    -0.69
    CAPÍTULO
    -0.69
    médiaire
    -0.69
    ċċ
    -0.68
    staticmethod
    -0.67
     Dons
    -0.66
    tg
    -0.66
    pagn
    -0.66
     circulación
    -0.66
    POSITIVE LOGITS
     spectrum
    3.05
    spectrum
    2.47
     Spectrum
    2.11
     spectra
    2.11
    Spectrum
    1.87
     espectro
    1.72
     spectral
    1.64
    谱
    1.43
    spectra
    1.41
     spek
    1.38
    Activations Density 0.043%

    No Known Activations