© 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. 34-GEMMASCOPE-RES-131K
    7. 65708
    Prev
    Next
    INDEX
    Explanations

    Windows UI XAML

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

    The neuron is detecting email address patterns (the username and “@” sequence).

    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
    StartCoroutine
    -0.85
     pasado
    -0.79
     additional
    -0.76
    ogramm
    -0.74
     collaborations
    -0.73
     ਹੋ
    -0.71
     claras
    -0.71
    dampak
    -0.71
     presentará
    -0.71
    ὲ
    -0.71
    POSITIVE LOGITS
    delingen
    0.79
     relat
    0.78
    ========
    0.78
     gui
    0.77
    awk
    0.76
    Occ
    0.76
    阿尔
    0.74
    nte
    0.73
     كث
    0.73
    Ꭺ
    0.73
    Activations Density 0.038%

    No Known Activations