© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1575
    Prev
    Next
    INDEX
    Explanations

    electromagnetic waves wavelength spectrum

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

    The neuron strongly activates on technical jargon related to optics and light—particularly terms naming parts of or measurements in infrared/laser and wavelength‐based systems.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ამართ
    0.59
     gön
    0.58
    🏡
    0.58
     الاجتما
    0.57
     제도
    0.57
     contratar
    0.57
     barter
    0.56
    雁
    0.56
     sonhos
    0.55
     afiliados
    0.55
    POSITIVE LOGITS
     wavelengths
    1.95
     wavelength
    1.92
     spectral
    1.87
    wavelength
    1.81
     spectra
    1.71
     spectrum
    1.64
    spectral
    1.64
     Spectral
    1.59
     спект
    1.58
    Spectral
    1.55
    Activations Density 0.268%

    No Known Activations