© 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. 86016
    Prev
    Next
    INDEX
    Explanations

    Airbus aircraft models

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

    The neuron detects mentions of the Airbus A380 model designation (the “A 3 8 0” token sequence).

    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
    '
    -2.38
    ’
    -2.20
     because
    -1.90
    но
    -1.80
     untuk
    -1.74
    —
    -1.74
    O
    -1.67
    ”？
    -1.67
    ーーー
    -1.65
     براي
    -1.64
    POSITIVE LOGITS
     waren
    1.88
     hagan
    1.83
    pecabe
    1.76
     mantenga
    1.75
     sahiptir
    1.72
     двумя
    1.69
     symbolize
    1.66
     WHICH
    1.66
     envejec
    1.66
     conlle
    1.65
    Activations Density 0.007%

    No Known Activations