© 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. 93756
    Prev
    Next
    INDEX
    Explanations

    metamaterials and related physics

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

    The neuron activates on occurrences of “plasmon” (and closely related technical terms in plasmonics) in scientific text.

    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
    seats
    -0.76
     Bead
    -0.75
     Rim
    -0.72
     seat
    -0.71
    newInstance
    -0.68
    Sap
    -0.68
    awang
    -0.68
    bead
    -0.68
    caf
    -0.68
    seat
    -0.67
    POSITIVE LOGITS
     meta
    1.23
    meta
    1.10
    Meta
    0.90
     metas
    0.89
     мета
    0.87
     méta
    0.86
     Meta
    0.86
     Lieblings
    0.84
    metas
    0.83
     macchina
    0.73
    Activations Density 0.066%

    No Known Activations