© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2810
    Prev
    Next
    INDEX
    Explanations

    actions following "always"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ″
    2.58
     circumstances
    2.50
     surgi
    2.49
    此之外
    2.45
    ം
    2.37
    openide
    2.34
    𝑛
    2.34
     ҳо
    2.32
    ">(</
    2.30
    an
    2.29
    POSITIVE LOGITS
    ज
    3.51
    ج
    3.10
    د
    3.09
    ри
    2.72
     пожалуйста
    2.47
    س
    2.45
    ى
    2.45
    firm
    2.44
    ट
    2.43
    há
    2.43
    Activations Density 0.095%

    No Known Activations