© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30816
    Prev
    Next
    INDEX
    Explanations

    plasmon resonance

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

    The neuron detects the word "plasmon" and its variants (plasmonic, plasmons) in scientific texts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    ᠡ
    -0.73
    pantalón
    -0.71
    寺
    -0.70
     IBOutlet
    -0.67
     reina
    -0.66
     Cattle
    -0.65
    ∇
    -0.65
    Ĵ
    -0.64
    UNTE
    -0.64
     хлеб
    -0.64
    POSITIVE LOGITS
     consolation
    0.78
     zá
    0.71
    tilus
    0.67
     הפ
    0.66
    berta
    0.66
     phosp
    0.65
     pull
    0.64
    ्स
    0.63
    estad
    0.62
    Respectfully
    0.62
    Activations Density 0.073%

    No Known Activations