© 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. 10-GEMMASCOPE-RES-131K
    7. 10900
    Prev
    Next
    INDEX
    Explanations

    web development JavaScript HTTP methods

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

    HTTP method attributes or keywords in programming code, particularly "HttpGet" and "HttpPost".

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

    The neuron fires on technology and API keywords—especially HTTP-related method attributes (e.g. HttpGet, HttpPost) and other tech names like Javascript.

    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
    öpfer
    -2.84
    ,’
    -2.80
     addition
    -2.61
    vantaged
    -2.52
     также
    -2.48
    ם
    -2.48
    愎
    -2.45
    richlet
    -2.42
    rhosis
    -2.38
    ций
    -2.36
    POSITIVE LOGITS
    ing
    4.09
    2
    3.03
    7
    3.03
    4
    3.03
    5
    2.83
    3
    2.78
    9
    2.75
     genaue
    2.64
     einzigartige
    2.59
     hohe
    2.55
    Activations Density 0.022%

    No Known Activations