© 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. 58615
    Prev
    Next
    INDEX
    Explanations

    email and web content

    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
    Belle
    -0.88
    机制
    -0.82
     Idol
    -0.79
     posted
    -0.79
    Visitors
    -0.77
     callers
    -0.74
    㠀
    -0.74
     carcinogenic
    -0.74
    loggedIn
    -0.72
     вироб
    -0.72
    POSITIVE LOGITS
     email
    1.03
     Email
    0.90
     unsubscribe
    0.82
    <!--[
    0.82
     Gmail
    0.82
    gmail
    0.81
    ﹣
    0.80
    campaign
    0.79
     inbox
    0.79
    email
    0.78
    Activations Density 0.017%

    No Known Activations