© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 100377
    Prev
    Next
    INDEX
    Explanations

    Hawaii locations

    np_acts-logits-general · gemini-2.5-flash-lite

    Hawaiian islands and vacation spots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     पाकिस्तान
    0.49
     Michigan
    0.49
     Antwerp
    0.47
     argent
    0.47
    Michigan
    0.47
     पाकिस्तानी
    0.47
     dowol
    0.46
    郗
    0.46
     pakistan
    0.46
     θερ
    0.45
    POSITIVE LOGITS
     Hawaiian
    1.61
     Maui
    1.57
     Hawai
    1.55
    Hawaii
    1.55
     Hawaii
    1.55
     Kauai
    1.55
    Maui
    1.48
     Honolulu
    1.45
     Oahu
    1.44
     Aloha
    1.25
    Activations Density 0.127%

    No Known Activations