© 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. 34-GEMMASCOPE-RES-131K
    7. 83383
    Prev
    Next
    INDEX
    Explanations

    distributed system state management

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

    This neuron fires on technical documentation and configuration keywords—section headings, component names, command parameters, and other key terms in docs or code.

    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
     Cabral
    -0.91
    西装
    -0.79
    شناس
    -0.78
     julk
    -0.77
    érêt
    -0.76
    ITIVE
    -0.76
    ających
    -0.75
     trofeo
    -0.75
    Hör
    -0.75
     사업
    -0.75
    POSITIVE LOGITS
     leader
    1.16
     Leader
    1.07
    Leader
    1.05
    leader
    1.02
     leadership
    0.95
     Raft
    0.94
     coordinator
    0.94
     coordinators
    0.91
    coord
    0.91
     metadata
    0.90
    Activations Density 0.045%

    No Known Activations