© 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. 37976
    Prev
    Next
    INDEX
    Explanations

    support ticket requests

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

    The neuron fires strongly on URL‐style patterns (e.g. “http://…/…?…=&…”), essentially detecting web addresses.

    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
    Sealed
    -0.73
    urches
    -0.71
    タイミング
    -0.68
    pageId
    -0.68
     গ
    -0.68
     schonmal
    -0.66
     Ziel
    -0.66
    abadi
    -0.66
    Costo
    -0.64
    HeaderComponent
    -0.64
    POSITIVE LOGITS
     ticket
    3.22
     tickets
    3.16
    ticket
    2.61
    Ticket
    2.58
    Tickets
    2.53
     Ticket
    2.52
     Tickets
    2.52
    tickets
    2.50
     ticketing
    2.06
     TICKET
    1.91
    Activations Density 0.067%

    No Known Activations