© 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-16K
    7. 3224
    Prev
    Next
    INDEX
    Explanations

    per capita

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     влия
    0.71
    繇
    0.68
     сход
    0.67
    因素
    0.65
     στη
    0.64
     வரு
    0.64
     काबू
    0.62
    씩
    0.60
     аппарат
    0.60
     உதவுக
    0.60
    POSITIVE LOGITS
     sendiri
    0.72
    正規品
    0.70
     refunds
    0.69
    hanahu
    0.69
     Edition
    0.69
     Refunds
    0.69
    rags
    0.68
    ylate
    0.68
    jesi
    0.68
     óta
    0.67
    Activations Density 1.940%

    No Known Activations