© 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. 90385
    Prev
    Next
    INDEX
    Explanations

    models and dynamics

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

    The neuron fires on technical terms and phrases related to mathematical or ecological models of infectious‐disease dynamics and epidemiology.

    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
     Appliance
    -0.85
    Edison
    -0.78
    utsches
    -0.76
    Psych
    -0.75
    YUV
    -0.75
     hua
    -0.74
     saxophone
    -0.74
     SAMPLE
    -0.74
     Haydn
    -0.73
     Psych
    -0.73
    POSITIVE LOGITS
     mathematical
    1.33
     population
    1.26
     models
    1.20
     Mathematical
    1.17
     model
    1.17
    Mathematical
    1.12
     age
    1.06
    getModel
    1.05
     dynamics
    1.04
     modeling
    1.02
    Activations Density 0.113%

    No Known Activations