© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32283
    Prev
    Next
    INDEX
    Explanations

    sender EventArgs

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

    The neuron spikes on the punctuation tokens (especially parentheses and commas) used to separate parameters in C# method signatures.

    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
    יפול
    -0.90
     approxim
    -0.89
    ۲۰
    -0.86
     ต้อง
    -0.85
     Camaro
    -0.85
     UPI
    -0.85
    ________,
    -0.84
    ויים
    -0.83
    исп
    -0.81
    *),
    -0.81
    POSITIVE LOGITS
     EventArgs
    1.38
    EventArgs
    1.16
     out
    1.10
     org
    0.98
     args
    0.95
     العرب
    0.92
     putting
    0.81
     System
    0.81
    𝘂
    0.80
    Compute
    0.79
    Activations Density 0.004%

    No Known Activations