© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58699
    Prev
    Next
    INDEX
    Explanations

    microwave engineering concepts

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

    The neuron activates on numerical technical specification terms—numbers paired with unit abbreviations (e.g. GHz, dB, W) as found in hardware or RF datasheet tables.

    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
     wires
    -0.77
     eye
    -0.73
    paper
    -0.73
     хозяй
    -0.71
     taught
    -0.71
     telephone
    -0.69
    カナ
    -0.68
    听着
    -0.68
    eye
    -0.68
     Americans
    -0.68
    POSITIVE LOGITS
     Microwave
    1.08
     microwave
    1.00
     waveguide
    0.96
    Microwave
    0.94
     GaAs
    0.91
     SMA
    0.87
     preposition
    0.85
    SMA
    0.82
     coaxial
    0.81
     bulkhead
    0.81
    Activations Density 0.035%

    No Known Activations