© 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. 22-GEMMASCOPE-RES-131K
    4. 104448
    Prev
    Next
    INDEX
    Explanations

    threads and synchronization

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

    This neuron fires on lines showing program output (console log entries), i.e. the printed “take 1,” “release 1,” “release 2,” and similar output strings.

    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
     pessoal
    -0.94
     kesä
    -0.90
    你了
    -0.90
     verdict
    -0.90
     if
    -0.90
    煲
    -0.87
    quinone
    -0.85
     actionPerformed
    -0.85
     निम्नलिखित
    -0.84
    tanie
    -0.84
    POSITIVE LOGITS
     competición
    1.16
     özellikleri
    1.11
    orius
    1.05
    contentView
    1.05
     akumulator
    1.04
     Glaube
    1.02
    Pada
    1.02
    < 
    1.01
    łoży
    1.01
    ῖς
    0.98
    Activations Density 0.025%

    No Known Activations