© 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. 92164
    Prev
    Next
    INDEX
    Explanations

    simulated annealing

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

    The neuron detects mentions of optimization algorithms and related technical terminology (e.g., simulated annealing, genetic algorithms, graph partitioning).

    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
     buoyancy
    -0.79
    Gator
    -0.76
    farers
    -0.75
     loon
    -0.72
    wifery
    -0.71
    righted
    -0.71
    硯
    -0.70
    \<^
    -0.69
     corrector
    -0.69
    ัติ
    -0.68
    POSITIVE LOGITS
     annealing
    2.22
    anne
    1.84
     Anne
    1.80
    Anne
    1.74
     anne
    1.73
    ANNE
    1.52
     simulated
    1.43
    Simulated
    1.38
     temperature
    1.34
     Simulated
    1.34
    Activations Density 0.009%

    No Known Activations