© 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. 22-GEMMASCOPE-RES-131K
    7. 33044
    Prev
    Next
    INDEX
    Explanations

    simultaneously, concurrently, in parallel

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

    The neuron strongly activates on technical/descriptive terms around digital data transmission or signal‐flow contexts (e.g. “modem,” “digital,” “information,” “transmitting,” “record multiple channels,” 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
    ಬ
    -0.82
     comunión
    -0.80
     especially
    -0.79
    Dopo
    -0.78
     naudoti
    -0.78
    après
    -0.77
    haltens
    -0.77
     Subsequent
    -0.77
    duit
    -0.76
    cía
    -0.74
    POSITIVE LOGITS
     simultaneously
    2.19
     simultaneous
    2.14
    Simult
    2.00
    simult
    1.99
    Meanwhile
    1.88
     Simultaneously
    1.87
     parallel
    1.78
     concurrently
    1.73
     simult
    1.72
     concurrent
    1.63
    Activations Density 0.097%

    No Known Activations