© 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. 84175
    Prev
    Next
    INDEX
    Explanations

    volatile, synchronized, synchronization

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

    The main thing this neuron does is find concurrency‐related keywords (notably “synchronized” and “volatile”).

    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
     echte
    -1.48
    蠖
    -1.47
    
    -1.43
    หรือ
    -1.40
    觚
    -1.38
    ໊
    -1.36
     itinéraire
    -1.33
    ⚌
    -1.32
     autre
    -1.29
     pegatinas
    -1.29
    POSITIVE LOGITS
    d
    1.52
    n
    1.46
     offers
    1.46
    on
    1.41
    が
    1.35
    b
    1.28
     allows
    1.27
    .
    1.23
    e
    1.23
    '
    1.23
    Activations Density 0.001%

    No Known Activations