© 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-262K
    7. 5875
    Prev
    Next
    INDEX
    Explanations

    primarily based on

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     dijadikan
    0.56
     进行
    0.53
     或者
    0.52
     جديدة
    0.52
    并在
    0.52
     llegando
    0.50
     وغ
    0.49
    並且
    0.49
     或
    0.49
     พร้อม
    0.48
    POSITIVE LOGITS
     primarily
    0.91
     solely
    0.87
     largely
    0.80
     mainly
    0.78
     chiefly
    0.78
     purely
    0.73
     exclusively
    0.73
    primarily
    0.72
     principalmente
    0.70
     principally
    0.70
    Activations Density 0.810%

    No Known Activations