© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1017
    Prev
    Next
    INDEX
    Explanations

    balloons and flight mechanics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     Dury
    0.85
     गांठ
    0.66
    玟
    0.66
     Leibniz
    0.66
    蚪
    0.65
    砌
    0.64
     亀
    0.64
    鄞
    0.63
     mobili
    0.63
     Chud
    0.63
    POSITIVE LOGITS
     aircraft
    4.02
     airplane
    3.94
     aviation
    3.88
    飛行
    3.84
     flight
    3.84
    飞行
    3.76
     Aircraft
    3.75
     항공
    3.72
     flights
    3.72
    飞机
    3.71
    Activations Density 1.515%

    No Known Activations