© 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. 10-GEMMASCOPE-RES-131K
    7. 15165
    Prev
    Next
    INDEX
    Explanations

    gmail email addresses

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

    The neuron activates strongly on email addresses at the “gmail.com” domain.

    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
    </h4>
    -2.78
     ซึ่ง
    -2.70
     ที่
    -2.59
    䊐
    -2.48
    淬
    -2.41
    ?’
    -2.39
     欣赏
    -2.38
    งิน
    -2.38
    尨
    -2.36
    鹋
    -2.34
    POSITIVE LOGITS
    蟊
    2.63
    ⦊
    2.61
    it
    2.55
     verſ
    2.34
    裡的
    2.31
    8
    2.25
    沵
    2.16
    B
    2.11
    un
    2.09
    to
    2.08
    Activations Density 0.004%

    No Known Activations