© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116287
    Prev
    Next
    INDEX
    Explanations

    client/request details

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

    This neuron fires on tokens that appear in the title and header lines of a StackOverflow question (e.g. “Q:”, “Possible Duplicate:”, “How”, “to”, “get”, “client”, “IP”, etc.).

    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
     historic
    -0.74
    OfDay
    -0.73
     истори
    -0.71
     historical
    -0.70
     period
    -0.70
     automobile
    -0.69
     GlobalKey
    -0.69
     akik
    -0.69
     Motorola
    -0.69
    佺
    -0.69
    POSITIVE LOGITS
     getClient
    1.01
     REMOTE
    1.01
     proxies
    1.00
    getClient
    0.97
    REMOTE
    0.96
     client
    0.88
    ClientSize
    0.85
    QUEST
    0.83
    getenv
    0.82
    Descrizione
    0.82
    Activations Density 0.010%

    No Known Activations