© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 523
    Prev
    Next
    INDEX
    Explanations

    Orlando, Disney, Orange County

    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
    Negative Logits
     Liverpool
    0.46
    Liverpool
    0.42
    षु
    0.41
    hepat
    0.41
     seafront
    0.40
     seaside
    0.39
    DoesNotExist
    0.39
     উচ্ছ
    0.39
    libr
    0.39
    肝
    0.39
    POSITIVE LOGITS
    Orlando
    1.13
     Orlando
    1.13
     UCF
    0.72
     Disney
    0.55
    Disney
    0.55
    Orange
    0.54
     disney
    0.50
    🍊
    0.50
    柑
    0.49
     Orange
    0.48
    Activations Density 0.007%

    No Known Activations