© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 3843
    Prev
    Next
    INDEX
    Explanations

    sentence structure components

    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_16_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
     &
    0.57
    )
    0.55
     a
    0.54
     CASE
    0.51
     an
    0.50
     -
    0.49
    KA
    0.49
    ]
    0.49
     TED
    0.48
    0
    0.47
    POSITIVE LOGITS
    ون
    0.60
     ጥቅ
    0.57
     不需要
    0.56
    不必
    0.55
    片段
    0.53
     বাক্য
    0.53
    不
    0.53
    يا
    0.52
    不清
    0.52
     ينت
    0.52
    Activations Density 0.769%

    No Known Activations