© 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. 2263
    Prev
    Next
    INDEX
    Explanations

    email addresses

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

    The neuron fires on domain or organization name tokens found in email addresses or URLs (e.g. “google,” “com,” “microsoft,” etc.).

    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
    _/
    -1.21
    /
    -1.01
    /¯
    -1.01
    !/
    -0.95
    ²/
    -0.93
    /}.
    -0.93
    //!
    -0.88
    icolo
    -0.85
    /";
    -0.84
    ificados
    -0.84
    POSITIVE LOGITS
     email
    1.63
     mail
    1.51
     Email
    1.41
     emails
    1.38
    Email
    1.28
    mail
    1.26
    email
    1.21
     gmail
    1.18
     mailbox
    1.15
     Emails
    1.15
    Activations Density 0.059%

    No Known Activations