© 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. 98146
    Prev
    Next
    INDEX
    Explanations

    PSO, inertia, particles

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

    The neuron is tuned to detect technical optimization terminology—especially mentions of “Particle Swarm Optimization” and its related keywords (e.g. PSO, velocity, particles, position update).

    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
     Ox
    -0.79
    play
    -0.76
     ox
    -0.75
     ماشین
    -0.74
     Oracle
    -0.74
    *)&
    -0.74
    нк
    -0.72
    parenting
    -0.71
     Machine
    -0.71
    carpus
    -0.71
    POSITIVE LOGITS
     PSO
    1.20
     constriction
    1.15
     particles
    0.96
     Particles
    0.95
    ertia
    0.94
    PSO
    0.90
     global
    0.89
     जानकारी
    0.88
     inertia
    0.88
     particle
    0.86
    Activations Density 0.004%

    No Known Activations