© 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. 1841
    Prev
    Next
    INDEX
    Explanations

    celestial objects and size

    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
     ಪೊಲೀಸ
    0.84
    ச்சா
    0.77
    ോധ
    0.75
     ctrl
    0.73
     indoors
    0.73
     reinstate
    0.73
     कुर्
    0.72
     peserta
    0.72
    بيق
    0.71
     절
    0.71
    POSITIVE LOGITS
     galaxies
    1.92
     galaxy
    1.83
     astronomers
    1.80
     stars
    1.73
     Galaxies
    1.65
     supernovae
    1.65
     gravitational
    1.62
     stellar
    1.61
     galactic
    1.60
     supernova
    1.60
    Activations Density 0.386%

    No Known Activations