© 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. 29-GEMMASCOPE-2-RES-65K
    7. 2114
    Prev
    Next
    INDEX
    Explanations

    birth, born, family, generations

    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_29_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     AudioManager
    0.73
     वापर
    0.73
     الليل
    0.71
    င့်
    0.68
     anisotropic
    0.66
     اڈ
    0.66
     véh
    0.65
     adjustable
    0.65
    櫂
    0.64
     tranquilidad
    0.64
    POSITIVE LOGITS
     birth
    3.36
     born
    3.07
    birth
    2.95
     births
    2.86
    Birth
    2.81
     Birth
    2.79
    born
    2.71
    Born
    2.66
     Born
    2.62
    出生
    2.54
    Activations Density 0.393%

    No Known Activations