© 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. 76317
    Prev
    Next
    INDEX
    Explanations

    aircraft and aerospace components

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

    The neuron strongly activates on named organizations and proper-noun aviation/aircraft model identifiers (e.g. “Boeing,” “Airbus A380,” “Delta Air Lines Inc.”).

    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
    무
    -0.78
    ў
    -0.76
    enze
    -0.72
     Phy
    -0.71
     layui
    -0.70
    omethane
    -0.69
    DriverManager
    -0.69
     oldu
    -0.69
    评测
    -0.69
     avuto
    -0.69
    POSITIVE LOGITS
     aerospace
    1.48
     aircraft
    1.48
     Airbus
    1.41
     Boeing
    1.35
    Boeing
    1.23
     aeron
    1.21
     Aerospace
    1.20
    aircraft
    1.19
     airplane
    1.15
    Aircraft
    1.13
    Activations Density 0.059%

    No Known Activations