© 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. 34-GEMMASCOPE-RES-131K
    7. 93561
    Prev
    Next
    INDEX
    Explanations

    email addresses

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

    The neuron strongly activates on email address components (e.g. “@” signs and domain name tokens).

    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
     Wydawnictwo
    -0.74
    trand
    -0.74
    diti
    -0.73
    钵
    -0.72
     सर्
    -0.72
     Fell
    -0.72
    膜
    -0.71
     obispo
    -0.70
    NodeInfo
    -0.70
    hydrat
    -0.69
    POSITIVE LOGITS
     Yahoo
    2.02
     yahoo
    1.88
    Yahoo
    1.75
     Outlook
    1.70
    yahoo
    1.67
     outlook
    1.59
    outlook
    1.59
    hotmail
    1.52
    Outlook
    1.51
     AOL
    1.48
    Activations Density 0.037%

    No Known Activations