© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 31080
    Prev
    Next
    INDEX
    Explanations

    synthetic aperture radar

    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_all/layer_41_width_262k_l0_big
    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
     rejuvenated
    0.44
     kttt
    0.42
     Bxd
    0.40
    ικ
    0.40
    }{$
    0.40
     боле
    0.39
    莓
    0.39
     vested
    0.39
    
    0.39
     établie
    0.39
    POSITIVE LOGITS
     radar
    1.06
    Radar
    1.06
     Radar
    1.04
    Synthetic
    1.01
     SAR
    0.98
    SAR
    0.96
     Synthetic
    0.94
    radar
    0.91
     synthetic
    0.86
     radars
    0.86
    Activations Density 0.002%

    No Known Activations