© 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. 108063
    Prev
    Next
    INDEX
    Explanations

    atomic

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

    references to atomic operations or atomic synchronization in programming code.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron flags language around “atomic” or otherwise indivisible operations—e.g. journaling commits, atomic‐library imports, lock instructions, and other low‐level synchronization primitives.

    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
    chränkungen
    -0.86
    bles
    -0.71
     Phu
    -0.70
     Arist
    -0.70
    cisco
    -0.69
    UART
    -0.67
    QUADS
    -0.66
    รอง
    -0.65
    typeId
    -0.65
     tonight
    -0.65
    POSITIVE LOGITS
     atomic
    4.72
     Atomic
    4.16
    Atomic
    4.09
    atomic
    3.89
     atom
    3.84
    Atom
    3.38
     Atom
    3.33
    原子
    3.31
    atom
    3.27
     ATOM
    3.23
    Activations Density 0.080%

    No Known Activations