© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19875
    Prev
    Next
    INDEX
    Explanations

    .html and .aspx files

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

    The neuron fires on C#/.NET MVC code tokens—particularly namespace and class names, file extensions, framework types (e.g. Controller, Dictionary, ViewBag), and the punctuation (dots, underscores) that structure them.

    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
     even
    -1.48
    6
    -1.32
     lengu
    -1.30
     сын
    -1.30
    case
    -1.27
    :{},
    -1.25
    8
    -1.23
    <
    -1.23
     حتی
    -1.22
     esimerkiksi
    -1.21
    POSITIVE LOGITS
    ızlık
    1.36
    amerikanische
    1.36
     لقد
    1.34
    complished
    1.32
     деталей
    1.31
    cheiben
    1.27
    STILL
    1.27
     çok
    1.26
     Chbosky
    1.23
    denk
    1.23
    Activations Density 0.001%

    No Known Activations