© 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. 3248
    Prev
    Next
    INDEX
    Explanations

    http clients and protocols

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

    This neuron fires on mentions of the Apache/Android HTTP client library (e.g. package or class names like org.apache.http.client.HttpClient, HttpClient, HttpGet, 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
     pens
    -0.77
     dever
    -0.74
    Eyed
    -0.73
    testens
    -0.73
     poeta
    -0.73
    Читати
    -0.73
    Queries
    -0.73
     cages
    -0.73
     Prix
    -0.72
     diffused
    -0.72
    POSITIVE LOGITS
     protocol
    0.83
    protocol
    0.81
    client
    0.78
     client
    0.70
    靚
    0.69
    hill
    0.68
    bore
    0.66
     asistir
    0.66
    angé
    0.66
     organes
    0.65
    Activations Density 0.007%

    No Known Activations