© 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. 111317
    Prev
    Next
    INDEX
    Explanations

    Pacific islands and Fiji

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

    Polynesian island cultures

    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
    兗
    0.45
     Ростов
    0.43
    缙
    0.43
     गुजरात
    0.43
     Appalachian
    0.43
    荆
    0.43
     तुलना
    0.43
     ফৌজ
    0.42
     करोड़
    0.42
    燉
    0.42
    POSITIVE LOGITS
     Samoa
    1.16
     Polynesian
    1.12
     Fiji
    1.10
     Polynesia
    0.99
     Tonga
    0.95
     Vanuatu
    0.95
     Fij
    0.94
     Tahiti
    0.86
     Samo
    0.83
    Pacific
    0.79
    Activations Density 0.035%

    No Known Activations