© 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. 10-GEMMASCOPE-RES-131K
    7. 104681
    Prev
    Next
    INDEX
    Explanations

    aerodynamic flow and drag

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

    The neuron fires on specialized engineering or physics measurement terms—especially aerodynamic and fluid‐dynamics metrics like drag, lift, coefficients, airflow, and related technical jargon.

    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
     tersebut
    -1.18
     Belast
    -1.13
     mereka
    -1.13
     kemudian
    -1.12
     partici
    -1.08
     brancas
    -1.08
     Allí
    -1.07
    ياء
    -1.06
    窘
    -1.05
     творо
    -1.03
    POSITIVE LOGITS
    män
    1.27
     aerodynamic
    1.27
    )++;
    1.23
     wind
    1.23
    Kedua
    1.20
     if
    1.16
    while
    1.15
     profile
    1.13
     zbyt
    1.11
    風
    1.11
    Activations Density 0.080%

    No Known Activations