© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 63187
    Prev
    Next
    INDEX
    Explanations

    email and email addresses

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

    This neuron detects UI section headings or labels indicating popular or most-viewed/commented content (e.g. “Most Popular,” “Most Commented,” “Most Viewed”).

    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
    сторон
    -0.84
     Cartes
    -0.77
     uren
    -0.73
    jną
    -0.72
     cincin
    -0.72
    łom
    -0.71
     hvil
    -0.70
     Ern
    -0.69
     Franse
    -0.69
     Marburg
    -0.68
    POSITIVE LOGITS
     email
    7.63
     emails
    6.34
    email
    6.13
     Email
    6.00
    Email
    5.88
     emailed
    5.13
     emailing
    5.09
     EMAIL
    4.88
    EMAIL
    4.84
    getEmail
    4.28
    Activations Density 0.420%

    No Known Activations