© 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. 4098
    Prev
    Next
    INDEX
    Explanations

    from a

    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
    ."
    1.59
    ret
    1.55
    leg
    1.54
    ras
    1.53
    рі
    1.52
    chn
    1.50
    ря
    1.49
    erc
    1.48
    عد
    1.45
    .
    1.43
    POSITIVE LOGITS
     condado
    2.52
    ੀ
    2.51
    Tabpage
    2.47
    ONEDB
    2.43
     البيت
    2.36
    tattoo
    2.33
    ifizieren
    2.29
     inhom
    2.27
    皙
    2.27
     tây
    2.24
    Activations Density 0.122%

    No Known Activations