© 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. 98367
    Prev
    Next
    INDEX
    Explanations

    Gibbs free energy, enthalpy, temperature

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

    mathematical and scientific terminology related to thermodynamics and energy calculations.

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

    The neuron strongly activates on tokens that are part of mathematical or scientific notation—LaTeX-style symbols, variable names (e.g. Δ, G, H, T), operators, and numeric 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
     energy
    -1.35
     Energy
    -1.13
    energy
    -1.02
    Energy
    -1.00
     equilibrium
    -0.97
     turno
    -0.83
     ENERGY
    -0.82
    лі
    -0.82
    jednoc
    -0.77
     Bewertung
    -0.75
    POSITIVE LOGITS
    ادية
    0.88
    iosync
    0.87
    Gilla
    0.83
    MetaType
    0.82
     hvid
    0.81
     Sora
    0.80
    fns
    0.80
     들어
    0.79
    kuji
    0.78
    Flas
    0.78
    Activations Density 0.011%

    No Known Activations