© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39202
    Prev
    Next
    INDEX
    Explanations

    related to locks

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

    The neuron flags occurrences of synchronization primitives and lock/unlock operations (e.g. “lock,” “Lock,” “unlock,” mutex/RW‐lock names) 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_10/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
    f
    -1.76
     of
    -1.69
    v
    -1.61
    ны
    -1.53
     –
    -1.48
    ”
    -1.47
    VolleyError
    -1.40
    ”,
    -1.38
    m
    -1.34
    x
    -1.33
    POSITIVE LOGITS
    赑
    1.86
    
    1.59
     剧照
    1.56
     helyzet
    1.55
    ൪
    1.55
    卺
    1.53
    
    1.52
    Чтоб
    1.52
    шных
    1.50
    брь
    1.49
    Activations Density 0.020%

    No Known Activations