© 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-16K
    7. 11694
    Prev
    Next
    INDEX
    Explanations

    comprehending or understanding

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

    understanding of the

    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_16k_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
    Е
    0.89
    О
    0.75
    Кон
    0.68
    会议
    0.68
    ၊
    0.68
    见
    0.67
    𝙄
    0.67
    ngày
    0.66
     શિક્ષણ
    0.66
    né
    0.65
    POSITIVE LOGITS
     memahami
    0.85
    理解
    0.84
    Understand
    0.82
    /
    0.81
    ר
    0.80
     forstå
    0.78
     understood
    0.77
     Understand
    0.77
     Understanding
    0.77
     이해
    0.76
    Activations Density 0.202%

    No Known Activations