© 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. 10-GEMMASCOPE-RES-131K
    7. 127249
    Prev
    Next
    INDEX
    Explanations

    email addresses or domains

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

    The neuron specializes in spotting email‐address components (tokens like user names, “@” signs, and domain segments).

    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
    ...............
    -1.49
     ..........
    -1.44
     itself
    -1.37
     ...........
    -1.35
     ..............
    -1.34
     .............
    -1.34
     .........
    -1.33
     ...............
    -1.31
    that
    -1.31
    ..............
    -1.30
    POSITIVE LOGITS
     of
    1.90
    weitere
    1.63
    schon
    1.59
     nôtre
    1.52
    espero
    1.49
    danke
    1.38
    sowie
    1.34
     navigateur
    1.34
    Jahre
    1.34
     unleash
    1.33
    Activations Density 0.029%

    No Known Activations