© 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. 22-GEMMASCOPE-2-RES-65K
    7. 8843
    Prev
    Next
    INDEX
    Explanations

    structural formatting markers

    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_22_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    entially
    0.89
    0
    0.89
    2
    0.88
    quick
    0.88
    8
    0.88
    1
    0.84
     阅读全文
    0.83
    .}\
    0.83
    3
    0.81
    ‬‬
    0.81
    POSITIVE LOGITS
     Số
    1.10
    ↵↵
    1.09
     Wetlands
    1.09
     Educación
    1.09
     Debate
    1.07
     Matemática
    1.05
     Loại
    1.04
     Selección
    1.01
     Antioxid
    1.01
     Legend
    1.00
    Activations Density 0.160%

    No Known Activations