© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2735
    Prev
    Next
    INDEX
    Explanations

    past tense verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ลาย
    1.45
     (
    1.39
    ↵
    1.31
    น้ำ
    1.23
      
    1.21
     H
    1.17
    ยา
    1.15
     (?)
    1.13
       
    1.13
     N
    1.12
    POSITIVE LOGITS
     absolutamente
    1.96
     ዓይነ
    1.73
     ständig
    1.72
     seulement
    1.71
     asla
    1.70
    घरों
    1.66
     একেবারেই
    1.64
     কোনো
    1.60
     vastly
    1.60
     yalnızca
    1.59
    Activations Density 1.335%

    No Known Activations