© 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. 115816
    Prev
    Next
    INDEX
    Explanations

    email addresses and fields

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    リップ
    -0.85
    χ
    -0.84
     alloy
    -0.84
     geopolitical
    -0.82
     wooden
    -0.81
    oint
    -0.81
    xr
    -0.79
    sider
    -0.78
     cuộc
    -0.77
     Brücke
    -0.77
    POSITIVE LOGITS
     email
    3.38
    email
    2.38
     Email
    2.34
    Email
    2.28
     emails
    2.20
    getEmail
    2.08
    EmailAddress
    1.99
    EMAIL
    1.95
    邮箱
    1.86
    メール
    1.80
    Activations Density 0.026%

    No Known Activations