© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11279
    Prev
    Next
    INDEX
    Explanations

    email addresses

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

    This neuron detects parts of email addresses (usernames, dots, and the “@” symbol).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anden
    0.55
     annen
    0.52
     mos
    0.52
     °
    0.52
     concatenation
    0.51
     عَ
    0.51
    ភ្ជាប់
    0.50
    °.
    0.50
     সিলেটের
    0.50
     präsentiert
    0.50
    POSITIVE LOGITS
    ToArray
    0.63
    ၂
    0.57
    护理
    0.50
     Ernst
    0.49
    penalty
    0.49
    ਉ
    0.49
    同事
    0.48
     Ehe
    0.47
    Essentially
    0.47
     colleague
    0.46
    Activations Density 0.014%

    No Known Activations