© 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. 23653
    Prev
    Next
    INDEX
    Explanations

    API controller methods

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

    The neuron fires on C# ASP .NET Web/API controller declarations—especially the public method signatures decorated with [HttpGet], [Route], and related MVC attribute brackets.

    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
     javafx
    -0.91
    jspx
    -0.86
    Ajax
    -0.74
     cookie
    -0.73
    marginRight
    -0.73
     brasileira
    -0.73
     dissipate
    -0.72
    номи
    -0.71
     Espresso
    -0.71
    ochrom
    -0.70
    POSITIVE LOGITS
     PUT
    0.88
     retort
    0.86
     CORS
    0.80
     Frida
    0.78
     Oi
    0.76
     rotación
    0.76
     colorear
    0.76
    newItem
    0.75
    ाप
    0.75
    put
    0.74
    Activations Density 0.007%

    No Known Activations