© 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. 34-GEMMASCOPE-RES-131K
    7. 91418
    Prev
    Next
    INDEX
    Explanations

    flight and aircraft

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

    the main thing this neuron does is find references to aircraft or aerial operations.

    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
    Traveler
    -0.81
    Outside
    -0.78
     undergone
    -0.75
    禺
    -0.74
     Outside
    -0.74
     shipyard
    -0.73
    Missile
    -0.73
    ytt
    -0.73
     Traveler
    -0.72
     exud
    -0.71
    POSITIVE LOGITS
     over
    2.02
     flying
    1.95
     fly
    1.94
     overhead
    1.87
     flew
    1.87
     flight
    1.81
     flights
    1.74
    flying
    1.64
     над
    1.58
     aerial
    1.51
    Activations Density 0.025%

    No Known Activations