© 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. 17-GEMMASCOPE-2-RES-16K
    7. 3671
    Prev
    Next
    INDEX
    Explanations

    listing conjunctions and punctuation

    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_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     colorectal
    0.74
    teki
    0.73
     slime
    0.72
     monthly
    0.70
    itarian
    0.69
    organized
    0.68
    your
    0.68
     обще
    0.68
    Ive
    0.68
    갤
    0.67
    POSITIVE LOGITS
     ebenso
    0.98
     ხოლო
    0.96
     likewise
    0.94
     sebagainya
    0.93
     natomiast
    0.89
     나머
    0.89
     conversely
    0.88
     zatim
    0.88
     그렇지
    0.87
     Conversely
    0.87
    Activations Density 0.352%

    No Known Activations