© 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. 3444
    Prev
    Next
    INDEX
    Explanations

    language or foreign words

    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
    および
    1.39
     ఆర్థిక
    1.25
     számos
    1.22
    ʺ
    1.18
     および
    1.17
     באמצעות
    1.12
    ȩ
    1.11
    における
    1.09
    すなわち
    1.09
    ␥
    1.08
    POSITIVE LOGITS
     kinda
    1.51
     cuz
    1.42
     veggies
    1.41
     meds
    1.41
     ppl
    1.35
     lvl
    1.30
     vibe
    1.29
     bbq
    1.28
     cowardly
    1.27
     kids
    1.26
    Activations Density 0.100%

    No Known Activations