© 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. 10-GEMMASCOPE-RES-131K
    7. 118883
    Prev
    Next
    INDEX
    Explanations

    async programming

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

    the word "Async" in method names within programming code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron activates on the token “Async,” i.e. it detects occurrences of “Async” in the text.

    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
    轳
    -2.13
    genodigd
    -2.06
     funcionam
    -2.05
    辚
    -1.98
    錼
    -1.95
     órgãos
    -1.91
    ’,
    -1.89
    
    -1.89
    !’
    -1.83
     municípios
    -1.83
    POSITIVE LOGITS
    (
    2.66
    e
    2.27
    ].
    2.17
    $
    2.05
    ."
    2.03
    All
    1.95
    6
    1.93
    )
    1.93
    You
    1.91
    呦
    1.88
    Activations Density 0.001%

    No Known Activations