© 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. 10-GEMMASCOPE-RES-131K
    7. 103674
    Prev
    Next
    INDEX
    Explanations

    thermodynamic

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

    This neuron identifies scientific terminology related to thermodynamics and words beginning with "therm" (like thermoplastic, thermodynamic, thermotropic, thermophilic).

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

    The neuron detects occurrences of “therm”/“thermo”-related terms (e.g. thermodynamic, thermodynamics, thermoplastic).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     That
    -3.81
     We
    -3.58
     This
    -3.47
    -
    -3.06
    9
    -2.95
    2
    -2.94
     Only
    -2.88
     -
    -2.81
     By
    -2.72
     Get
    -2.70
    POSITIVE LOGITS
    ᯾
    3.59
    鷙
    3.20
    鱨
    3.08
    橚
    3.00
     typy
    2.97
    𓁹
    2.97
     твоя
    2.95
    ⚢
    2.94
    馘
    2.94
     新款
    2.89
    Activations Density 0.004%

    No Known Activations