© 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. 4122
    Prev
    Next
    INDEX
    Explanations

    thermodynamics and binding properties

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

    scientific text related to thermodynamics, chemistry, and binding properties with numerical measurements.

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

    The neuron is tuned to pick up thermochemistry/thermodynamics jargon—especially mentions of standard enthalpies of formation (ΔHƒ), related terms, and values.

    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
    ifferentiated
    -0.87
    clk
    -0.73
    ClickListener
    -0.71
    getitem
    -0.70
    互联网档案馆
    -0.70
    siert
    -0.69
    vangen
    -0.69
    akaian
    -0.69
    Alexa
    -0.69
    gras
    -0.69
    POSITIVE LOGITS
     enthalpy
    2.88
     enthal
    1.99
    enthal
    1.87
     Gibbs
    1.80
     heats
    1.70
     energy
    1.62
     heat
    1.59
     energies
    1.58
    Gibbs
    1.48
     entropy
    1.45
    Activations Density 0.093%

    No Known Activations