© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102295
    Prev
    Next
    INDEX
    Explanations

    electronic devices and equipment

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

    The neuron strongly activates on any form of the “electron” root—e.g. “electron,” “electronic,” “electronics,” “electronically,” and cognates.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ’
    -3.16
    s
    -2.45
    /
    -2.38
    ↵
    -2.05
     enam
    -1.98
     blossomed
    -1.89
      
    -1.87
     “
    -1.80
    </sup>
    -1.77
    y
    -1.69
    POSITIVE LOGITS
    珢
    2.58
    ৢ
    2.52
    ",
    2.52
     {
    2.48
    इटम
    2.30
    诹
    2.30
     memutus
    2.28
    ][:
    2.28
    🙍
    2.25
     \%)
    2.23
    Activations Density 0.037%

    No Known Activations