© 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. 34-GEMMASCOPE-RES-131K
    7. 23657
    Prev
    Next
    INDEX
    Explanations

    c# property and type declarations

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

    The neuron fires on code‐declaration keywords—particularly “public” and “enum”—i.e. it identifies lines where class members or enums are being declared.

    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
     اكتوبر
    -0.93
    lıyor
    -0.88
     tapi
    -0.84
    crimson
    -0.82
    انظر
    -0.81
    ユニクロ
    -0.79
    無い
    -0.79
    　↓
    -0.79
    Ignoring
    -0.78
    Much
    -0.77
    POSITIVE LOGITS
     Nullable
    1.95
    Nullable
    1.29
    System
    1.00
     System
    0.94
    ="#"
    0.93
    nullable
    0.91
     short
    0.88
     Lenovo
    0.85
     string
    0.84
    short
    0.84
    Activations Density 0.002%

    No Known Activations