© 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. 77180
    Prev
    Next
    INDEX
    Explanations

    HTTP request or response objects

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

    The neuron fires on occurrences of “http”/“HTTP” (including code-style namespace tokens like “http::” or “HTTP” in library/API calls).

    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
     area
    -0.80
     Pier
    -0.73
     стъ
    -0.72
    ianas
    -0.70
     Books
    -0.69
     Chemical
    -0.69
     port
    -0.66
     id
    -0.66
     kê
    -0.66
    t
    -0.66
    POSITIVE LOGITS
    gafas
    0.91
     message
    0.90
     avaliar
    0.88
    VolleyError
    0.88
    誒
    0.85
     fraî
    0.85
    воре
    0.84
     butik
    0.83
     paquetes
    0.82
    XmlRootElement
    0.81
    Activations Density 0.048%

    No Known Activations