© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 101953
    Prev
    Next
    INDEX
    Explanations

    .com email addresses

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

    email addresses and website domains, particularly those associated with news organizations.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron strongly activates on publication metadata—especially URLs, email addresses, author/byline tokens, and other dateline or source‐attribution elements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     by
    -1.95
     (
    -1.68
     ,
    -1.58
     verschiedenen
    -1.41
    (
    -1.36
     :
    -1.34
    .
    -1.32
     zahlreichen
    -1.26
     -
    -1.25
     I
    -1.24
    POSITIVE LOGITS
    塒
    1.59
     cinto
    1.57
     afront
    1.55
    eload
    1.52
    Ꮂ
    1.52
     tids
    1.50
     a
    1.48
     concerne
    1.45
     pulsa
    1.43
    takings
    1.42
    Activations Density 0.014%

    No Known Activations