© 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. 54337
    Prev
    Next
    INDEX
    Explanations

    space probe missions and discovery

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

    The neuron responds to technical terms related to space exploration (e.g. interplanetary, probe, spacecraft, NASA, Voyager).

    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
     orbiting
    -0.81
     compressors
    -0.71
     Trips
    -0.69
    koma
    -0.68
    зовать
    -0.68
     Navidad
    -0.67
    bitro
    -0.67
     Subsequent
    -0.66
    getNext
    -0.66
     fantasies
    -0.66
    POSITIVE LOGITS
     Voyager
    1.39
     Deep
    0.87
     fallas
    0.85
     Pioneer
    0.84
    kil
    0.81
     金
    0.80
     phenyl
    0.78
     العراق
    0.78
    ceptions
    0.78
    Deep
    0.78
    Activations Density 0.010%

    No Known Activations