© 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. 91595
    Prev
    Next
    INDEX
    Explanations

    Rx `Observer`/`Observable`/`Mono`

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

    This neuron fires on code tokens, especially API class and method names (notably Bluetooth LE/RxJava identifiers like “Ble”, “RxBleDevice”, “scanSubscription”, “subscribe”, 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_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
     Lev
    -0.90
     involunt
    -0.76
     cump
    -0.75
    нім
    -0.74
     Stein
    -0.73
     magnetic
    -0.72
    Lev
    -0.69
     mancha
    -0.69
    IGEN
    -0.69
     lev
    -0.69
    POSITIVE LOGITS
     AIAA
    0.96
     disposable
    0.94
     Rx
    0.94
    Disposable
    0.91
    Rx
    0.90
    posables
    0.88
     rx
    0.88
     Disposable
    0.86
     desecha
    0.86
    Emission
    0.86
    Activations Density 0.020%

    No Known Activations