© 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. 10-GEMMASCOPE-RES-131K
    7. 112923
    Prev
    Next
    INDEX
    Explanations

    systems

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

    the word "system" in technical and patent documents, particularly when describing computing, telecommunication, or engineering systems.

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

    The neuron is triggered by mentions of technical “system” constructs (e.g. data-processing systems, monitoring systems, network/telecommunications systems).

    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
    (!__
    -1.50
    क्र
    -1.43
    iligung
    -1.42
    мку
    -1.39
     finishes
    -1.34
     प्रोड
    -1.34
    ctuaries
    -1.34
    ются
    -1.34
    itaires
    -1.32
    ilà
    -1.30
    POSITIVE LOGITS
    鱟
    1.74
     Pediat
    1.52
    </i>
    1.50
    [
    1.48
     yöne
    1.46
    (
    1.45
    {
    1.45
    _
    1.43
    
    1.39
    絰
    1.38
    Activations Density 0.092%

    No Known Activations