© 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. 22-GEMMASCOPE-RES-131K
    7. 54427
    Prev
    Next
    INDEX
    Explanations

    ViewBag, TempData, Q, Mice, You, 1

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

    This neuron detects references to ASP.NET MVC state‐passing objects (e.g. ViewBag, ViewData, TempData).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     from
    -1.74
     réus
    -1.51
     like
    -1.47
    부터
    -1.47
     its
    -1.44
     their
    -1.40
     all
    -1.36
     When
    -1.35
     Füßen
    -1.34
    ركات
    -1.34
    POSITIVE LOGITS
     cũng
    1.45
    .
    1.41
     possib
    1.40
    同时也
    1.39
     suport
    1.34
     cata
    1.32
    plates
    1.31
     apar
    1.30
     peo
    1.30
    presents
    1.30
    Activations Density 0.000%

    No Known Activations