© 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. 106515
    Prev
    Next
    INDEX
    Explanations

    Microsoft Exchange/Outlook/mailbox

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

    The neuron flags tokens that contain numeric characters (i.e. any digit‐based token).

    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
     paid
    -0.79
    paid
    -0.78
    Bearbeiten
    -0.75
     ही
    -0.75
    endente
    -0.73
    omethyl
    -0.72
     berp
    -0.70
    ूर
    -0.69
     local
    -0.68
    цам
    -0.68
    POSITIVE LOGITS
     Exchange
    1.06
    OWA
    1.03
     mailbox
    1.02
    Exchange
    1.01
    DAG
    0.96
    owa
    0.94
     Outlook
    0.91
     EXCHANGE
    0.87
    WebApp
    0.85
    exchange
    0.80
    Activations Density 0.079%

    No Known Activations