© 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. 48289
    Prev
    Next
    INDEX
    Explanations

    fighter aircraft

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

    The neuron is specialized to pick up mentions of military aircraft—especially fighter jets (e.g. Typhoon, “scrambled jets,” etc.).

    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
    船
    -0.90
    bigint
    -0.84
     船
    -0.81
     。
    -0.81
     bateau
    -0.79
    Ὀ
    -0.78
    汽车
    -0.77
    BTS
    -0.76
     yacht
    -0.75
     Voyages
    -0.74
    POSITIVE LOGITS
     fighter
    1.95
    fighter
    1.52
     Fighter
    1.51
     fighters
    1.43
    Fighter
    1.41
     supersonic
    1.19
     aircraft
    1.17
     MiG
    1.15
     Mirage
    1.11
     jets
    1.10
    Activations Density 0.034%

    No Known Activations