© 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. 1897
    Prev
    Next
    INDEX
    Explanations

    requires huge, plays key, is decision

    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
     Pentru
    0.55
    手动
    0.52
     možete
    0.51
     Для
    0.51
    Для
    0.50
    Д
    0.49
    П
    0.49
     môžete
    0.49
     Ovaj
    0.48
    Г
    0.48
    POSITIVE LOGITS
     patriarchal
    0.39
     свое
    0.35
    willing
    0.32
     fundamental
    0.31
     unor
    0.31
    explored
    0.30
     kehidupan
    0.30
     mundane
    0.30
     awkward
    0.30
    ленными
    0.30
    Activations Density 0.107%

    No Known Activations