© 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. 45622
    Prev
    Next
    INDEX
    Explanations

    satellite and ground communication systems

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

    The neuron strongly activates on technical aerospace terms—especially words relating to satellites, ground‐to‐space propagation, missions, and associated systems.

    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
    sms
    -0.73
    álně
    -0.73
    >>()
    -0.71
     Buat
    -0.71
    SMS
    -0.71
    zoll
    -0.69
     disparate
    -0.68
     perang
    -0.66
    tizing
    -0.66
    rijk
    -0.66
    POSITIVE LOGITS
     ground
    1.16
     receive
    0.99
     links
    0.94
    plink
    0.91
     Ground
    0.90
     enlaces
    0.86
     microwave
    0.85
     down
    0.85
     link
    0.84
    AOS
    0.84
    Activations Density 0.028%

    No Known Activations