© 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. 108975
    Prev
    Next
    INDEX
    Explanations

    Holiday Punch

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

    This neuron activates on “return” statements in code.

    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
     it
    -1.04
    úč
    -1.00
    adalu
    -0.94
     their
    -0.94
     its
    -0.90
    ขอบคุณ
    -0.89
    nyataan
    -0.84
    ด้วย
    -0.84
    ции
    -0.84
    幼児
    -0.82
    POSITIVE LOGITS
    if
    1.27
    ਗ਼
    1.11
     этого
    1.08
     russischen
    1.05
     regina
    1.03
     cappuccio
    1.02
    this
    1.02
     '-'
    1.01
     exper
    0.99
    try
    0.99
    Activations Density 0.001%

    No Known Activations