© 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. 3280
    Prev
    Next
    INDEX
    Explanations

    numbers and code constructs

    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
     اوف
    0.79
     желания
    0.79
     길이가
    0.76
     delantero
    0.76
     ο
    0.76
     !\
    0.74
    腧
    0.72
     Μα
    0.72
     retângulo
    0.71
     goles
    0.71
    POSITIVE LOGITS
    Pub
    0.68
     स्‍टार
    0.67
     rumours
    0.66
     muse
    0.66
     understatement
    0.65
     biographer
    0.63
    ዱ
    0.62
    शिक
    0.61
     wedges
    0.61
    ۔
    0.60
    Activations Density 0.425%

    No Known Activations