© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1545
    Prev
    Next
    INDEX
    Explanations

    flight and aviation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wasserstein
    0.55
    ꫝ
    0.54
     Ambedkar
    0.52
    paredStatement
    0.52
    ປັນ
    0.52
    🧟
    0.52
     GDPPC
    0.52
    銭
    0.52
     সাম্প্রদায়িক
    0.51
     കോടതി
    0.51
    POSITIVE LOGITS
    飛行
    1.72
     aircraft
    1.63
     flight
    1.52
     airplane
    1.52
     flying
    1.50
    飞行
    1.48
     airplanes
    1.41
     aviation
    1.40
    Aircraft
    1.40
     Flight
    1.38
    Activations Density 0.379%

    No Known Activations