© 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. 92304
    Prev
    Next
    INDEX
    Explanations

    code attributes and syntax

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

    The neuron fires on occurrences of the “DisplayFor” helper (e.g. Html.DisplayFor) in ASP.NET MVC code.

    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
     comes
    -0.98
     other
    -0.83
     meticulously
    -0.82
     strade
    -0.82
     those
    -0.81
     contributes
    -0.79
    ዶ
    -0.78
     any
    -0.75
    เนื้อ
    -0.74
     might
    -0.73
    POSITIVE LOGITS
    龉
    1.05
     sleepy
    0.92
    部分を
    0.81
     asian
    0.80
     proprietor
    0.80
     совсем
    0.79
     indian
    0.79
     soooo
    0.78
     Argu
    0.78
    hap
    0.77
    Activations Density 0.002%

    No Known Activations