© 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. 35879
    Prev
    Next
    INDEX
    Explanations

    C# property definitions

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

    The neuron fires strongly on the C# “get;” accessor in property definitions, i.e. auto‐property getter declarations.

    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
    ſſen
    -2.41
    婓
    -2.34
     rafra
    -2.14
     rafraî
    -2.13
     kompati
    -2.13
    鈊
    -2.11
    𓆜
    -2.09
    
    -2.08
    Zubereitung
    -2.05
    豋
    -2.03
    POSITIVE LOGITS
    n
    2.23
    v
    1.95
    s
    1.93
    ;
    1.91
    ↵↵
    1.87
    r
    1.80
    A
    1.80
    q
    1.79
    o
    1.78
    ,'
    1.76
    Activations Density 0.002%

    No Known Activations