© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65049
    Prev
    Next
    INDEX
    Explanations

    density-functional theory and calculations

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

    computational chemistry and quantum physics terminology, especially related to density functional theory (DFT).

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

    The neuron detects technical mentions of density functional theory (DFT) and related van der Waals/dispersion‐corrected computational chemistry methods.

    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
    ztal
    -0.71
     waterway
    -0.70
     CMS
    -0.70
     abgeschlossen
    -0.69
    ěst
    -0.68
    fible
    -0.67
    通常の
    -0.66
     Litchfield
    -0.65
     chelsea
    -0.65
    フレ
    -0.65
    POSITIVE LOGITS
     functional
    1.05
     EXCHANGE
    1.02
    LDA
    1.01
     LDA
    0.96
    Functional
    0.91
     exchange
    0.89
     Kohn
    0.87
     xc
    0.84
    Exchange
    0.84
     Exchange
    0.84
    Activations Density 0.038%

    No Known Activations