© 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-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 3916
    Prev
    Next
    INDEX
    Explanations

    Maori and New Zealand terms

    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_53_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
     Schell
    0.45
     Novosibirsk
    0.45
     YORK
    0.44
    䣬
    0.43
     अफ्रीका
    0.42
     corris
    0.42
     можли
    0.42
    🐫
    0.42
    เซอร์
    0.42
     جوجل
    0.42
    POSITIVE LOGITS
     Māori
    1.80
     Maori
    1.46
     whakap
    1.44
     Mā
    1.27
     korero
    1.27
     Kā
    1.21
     whaka
    1.16
     mā
    1.16
     whak
    1.14
     whakam
    1.10
    Activations Density 0.009%

    No Known Activations