© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11757
    Prev
    Next
    INDEX
    Explanations

    planets, celestial bodies, space missions

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

    The neuron strongly activates on technical aerospace terms—especially spacecraft‐related equipment names and mission acronyms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     servicemen
    0.59
     lineman
    0.59
    🚅
    0.57
    🍣
    0.56
    лід
    0.55
     Bahnhof
    0.55
    🚄
    0.55
    鮨
    0.55
    synchronized
    0.54
     एसएस
    0.54
    POSITIVE LOGITS
     Mars
    1.30
    Mars
    1.23
     crater
    1.14
     rover
    1.12
     mars
    1.07
    Rover
    1.07
     craters
    1.06
     lunar
    1.05
    Venus
    1.05
     Martian
    1.04
    Activations Density 0.150%

    No Known Activations