© 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. 34-GEMMASCOPE-RES-131K
    7. 76432
    Prev
    Next
    INDEX
    Explanations

    gmail email addresses

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

    The neuron fires on tokens that are parts of email addresses (i.e. the “@” plus surrounding username/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_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
     such
    -1.23
    both
    -1.13
    によって
    -0.95
    抱怨
    -0.88
     רק
    -0.87
    がなく
    -0.86
    tabli
    -0.85
     sentimenti
    -0.84
    其他
    -0.84
    without
    -0.82
    POSITIVE LOGITS
    gmail
    3.33
     gmail
    2.63
     Gmail
    1.86
    yahoo
    1.84
    Gmail
    1.61
     Google
    1.51
    hotmail
    1.42
     google
    1.41
     yahoo
    1.23
    Google
    1.16
    Activations Density 0.013%

    No Known Activations