© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7090
    Prev
    Next
    INDEX
    Explanations

    Hawaiian islands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_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
     یور
    0.81
    augment
    0.81
    铅
    0.81
     DeepCollection
    0.79
     ஜெ
    0.77
    level
    0.76
    CHF
    0.73
     Gand
    0.73
    range
    0.73
    闫
    0.73
    POSITIVE LOGITS
     Hawaii
    2.54
     Hawaiian
    2.41
    Hawaii
    2.33
     Maui
    2.14
     Hawai
    2.12
     Honolulu
    2.10
     Oahu
    2.08
     Kauai
    1.93
     Aloha
    1.90
     Polynesian
    1.78
    Activations Density 0.207%

    No Known Activations