© 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. 1008
    Prev
    Next
    INDEX
    Explanations

    brazilian and Portuguese context

    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
    ้น
    0.52
     egregious
    0.46
     subconsciously
    0.46
    եր
    0.44
    Britain
    0.43
     wounding
    0.43
    Alchemy
    0.43
    ክ
    0.43
     አንድ
    0.42
    Alaska
    0.42
    POSITIVE LOGITS
     Brazilian
    1.63
     São
    1.62
     brazilian
    1.54
     Brasília
    1.52
     Conselho
    1.52
     Brasil
    1.48
    Brazilian
    1.45
     João
    1.45
     Projeto
    1.45
     União
    1.45
    Activations Density 0.032%

    No Known Activations