© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7089
    Prev
    Next
    INDEX
    Explanations

    molecular dynamics simulations

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

    text related to scientific computational methods such as molecular dynamics simulations or other modeling approaches.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron identifies explicit mentions of molecular-dynamics simulation studies (e.g. “molecular dynamics simulations”).

    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
    |}{\
    -0.90
     Soccerway
    -0.88
     experimenting
    -0.83
    unhofer
    -0.76
    릉
    -0.74
    caux
    -0.73
    ^{-}\
    -0.73
     experimentation
    -0.72
    trash
    -0.70
    TestBed
    -0.70
    POSITIVE LOGITS
     ato
    1.45
     MD
    1.38
     simulation
    1.38
     simulations
    1.34
    MD
    1.27
    Simulation
    1.16
     Simulation
    1.15
    模拟
    1.10
    Ato
    1.07
    atom
    1.06
    Activations Density 0.080%

    No Known Activations