© 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. 67711
    Prev
    Next
    INDEX
    Explanations

    WPF binding and ViewModel code

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

    The neuron flags MVVM–style C# code keywords (e.g. ViewModel, Base, Binding, Command, Input) and other data‐binding/class‐declaration tokens.

    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
    -1.35
    malı
    -1.10
     each
    -1.08
     these
    -1.06
     nineteen
    -0.98
     other
    -0.95
    these
    -0.92
    に行ってきました
    -0.91
     because
    -0.91
     Максима
    -0.91
    POSITIVE LOGITS
     любо
    1.05
    ጢ
    1.04
    Action
    1.02
    arini
    1.02
     action
    1.01
     lymphocytes
    1.00
    icza
    1.00
    ">
    0.98
     children
    0.98
     reactivity
    0.97
    Activations Density 0.007%

    No Known Activations