© 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. 34-GEMMASCOPE-RES-131K
    4. 103365
    Prev
    Next
    INDEX
    Explanations

    Microsoft DbContext properties

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

    The neuron activates on capitalized library or framework type names (e.g. Entity, Configuration, Mvc, Builder, Moq) in code, i.e. references to external packages or namespaces.

    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
     had
    -0.74
     develop
    -0.74
     all
    -0.74
     still
    -0.73
    andReturn
    -0.73
    喫茶
    -0.72
    ={}
    -0.72
     машин
    -0.72
     commonly
    -0.72
     procedures
    -0.72
    POSITIVE LOGITS
    occasione
    1.00
     nombreuses
    0.89
     NEL
    0.88
     LIN
    0.85
     giacca
    0.83
    ἷ
    0.82
    Includes
    0.82
    Healing
    0.82
     tà
    0.81
    Microsoft
    0.80
    Activations Density 0.011%

    No Known Activations