© 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. 31-GEMMASCOPE-2-RES-65K
    7. 5289
    Prev
    Next
    INDEX
    Explanations

    language that discusses gender differences in physical strength and performance.

    oai_token-act-pair · gpt-4o-miniTriggered by @gersonkroiz

    explaining why

    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_31_width_65k_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
    ໂດຍ
    0.42
    dataLayer
    0.41
     либо
    0.41
     irgendwo
    0.39
     ACS
    0.38
    ACS
    0.37
    ])[
    0.37
    RS
    0.37
    Savings
    0.36
    Ⅼ
    0.36
    POSITIVE LOGITS
    那么多
    0.92
    这么多
    0.91
    這麼
    0.87
     why
    0.85
    如此
    0.82
     tantos
    0.81
     so
    0.80
     এত
    0.80
    这么
    0.80
    为什么
    0.80
    Activations Density 0.399%

    No Known Activations