© 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. 40-GEMMASCOPE-2-RES-262K
    7. 1627
    Prev
    Next
    INDEX
    Explanations

    sat followed by ay, ire, or r

    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_40_width_262k_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
    一座
    0.41
     iguais
    0.39
    󠁷
    0.38
    
    0.38
    تالي
    0.38
    峣
    0.38
     Filter
    0.37
     CheckException
    0.37
    ⺊
    0.37
     परिषद
    0.37
    POSITIVE LOGITS
     Sat
    0.90
     sat
    0.89
    Sat
    0.86
     SAT
    0.86
    sat
    0.81
     satellites
    0.79
     sats
    0.79
     satt
    0.75
     Satt
    0.74
     satellite
    0.73
    Activations Density 0.009%

    No Known Activations