© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 16-GEMMASCOPE-2-RES-16K
    7. 739
    Prev
    Next
    INDEX
    Explanations

    you and related

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

    you give or produce

    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_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ي
    1.23
     for
    1.20
     nó
    1.17
    يلا
    1.17
    يها
    1.09
     meurt
    1.06
    يان
    1.05
     lanç
    1.03
     regrett
    1.03
     incend
    1.03
    POSITIVE LOGITS
    0
    1.72
     you
    1.36
    you
    1.20
    ill
    1.14
    1
    1.11
    ur
    1.10
    :
    1.10
    or
    1.05
     yourself
    1.05
    AH
    1.00
    Activations Density 1.790%

    No Known Activations