© 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-262K
    7. 30561
    Prev
    Next
    INDEX
    Explanations

    translation of foreign phrases

    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_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
     impacto
    0.38
     u
    0.37
     kunci
    0.36
     S
    0.34
     O
    0.34
     McCulloch
    0.33
    スペック
    0.33
     eventually
    0.33
    T
    0.33
    Eventually
    0.33
    POSITIVE LOGITS
    amblea
    0.41
    翻译
    0.40
    㞖
    0.40
     ਹੈ
    0.38
    譯
    0.38
     অনুবাদ
    0.38
    ர்ப்பு
    0.37
    再一次
    0.37
    ⸨
    0.37
    necklace
    0.37
    Activations Density 0.218%

    No Known Activations