© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 27138
    Prev
    Next
    INDEX
    Explanations

    `synchronized` and `volatile` keywords

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

    The neuron strongly activates on programming‐language type and storage‐class qualifiers (e.g. volatile, synchronized, uniform/mediump, __host__/__device__, JLabel, etc.).

    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
    ׅ
    -1.25
     our
    -1.25
     naše
    -1.16
    🚱
    -1.16
     teneur
    -1.15
     précédente
    -1.15
     그것
    -1.13
    狁
    -1.13
    蹙
    -1.11
     насељу
    -1.10
    POSITIVE LOGITS
     and
    1.68
     how
    1.37
     of
    1.18
    ,
    1.18
     such
    1.08
    lateinit
    1.06
    之所
    1.02
     a
    1.01
     void
    1.00
     whether
    0.99
    Activations Density 0.007%

    No Known Activations