© 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. 4165
    Prev
    Next
    INDEX
    Explanations

    contractions and common phrases

    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
     transform
    1.78
     dev
    1.74
     community
    1.70
     from
    1.63
    선
    1.63
     re
    1.62
    pen
    1.57
     form
    1.56
    ,
    1.56
    .
    1.53
    POSITIVE LOGITS
     পরিমাণে
    2.81
     топлива
    2.56
     necesidades
    2.46
     quantidades
    2.44
    quantidade
    2.43
     estoque
    2.41
     quantidade
    2.38
     épu
    2.37
     dinheiro
    2.37
     almacen
    2.35
    Activations Density 0.152%

    No Known Activations