© 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. 27867
    Prev
    Next
    INDEX
    Explanations

    maritime locations and destinations

    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
     দিনাজপুর
    0.55
    崞
    0.52
    云南
    0.51
     সিলেট
    0.48
    
    0.47
     बरेली
    0.46
     Новосибир
    0.46
    лянчук
    0.45
     রংপুর
    0.45
    鹿児島
    0.45
    POSITIVE LOGITS
     البحر
    0.48
    宁波
    0.44
     ferry
    0.41
     Burnham
    0.40
     yacht
    0.39
     maritime
    0.39
     seaw
    0.39
    澥
    0.39
     Harbour
    0.38
     تعريف
    0.38
    Activations Density 0.006%

    No Known Activations