© 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. 38626
    Prev
    Next
    INDEX
    Explanations

    aerodynamic airfoil performance

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

    The neuron flags numeric tokens—that is, digit sequences representing measurements or quantities.

    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
     monnaie
    -0.81
    Morse
    -0.80
    órc
    -0.80
     súng
    -0.77
     Earthquake
    -0.76
    MENTE
    -0.75
    IImage
    -0.75
    IGF
    -0.74
    ppings
    -0.74
    ưở
    -0.73
    POSITIVE LOGITS
     aerodynamic
    3.19
     aer
    2.33
     aero
    2.11
     Aer
    2.08
    aer
    2.03
    Aer
    1.97
     аэро
    1.96
     aéro
    1.79
     drag
    1.75
    aero
    1.73
    Activations Density 0.081%

    No Known Activations