© 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. 48642
    Prev
    Next
    INDEX
    Explanations

    email addresses

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

    The neuron fires on the “@” symbol—i.e. it detects email addresses.

    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
    and
    -1.06
     to
    -1.06
     подготовка
    -0.97
     both
    -0.97
     Только
    -0.96
    mean
    -0.96
    most
    -0.95
    f
    -0.94
     Both
    -0.94
    𝓼
    -0.93
    POSITIVE LOGITS
     gmail
    1.30
    ＊＊＊
    1.16
    スポンサーリンク
    1.15
    もうすぐ
    1.14
     nossa
    1.13
    gmail
    1.13
     더
    1.13
     먹
    1.13
    ＝＝＝＝
    1.12
    Depuis
    1.09
    Activations Density 0.025%

    No Known Activations