© 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. 10354
    Prev
    Next
    INDEX
    Explanations

    defense

    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
     لاکھ
    2.90
    뗑
    2.76
    даря
    2.75
    په
    2.71
    උ
    2.70
    ද්ග
    2.61
     gpointer
    2.59
     выполнен
    2.58
    ओं
    2.56
    ց
    2.55
    POSITIVE LOGITS
     ENO
    2.35
     instruction
    2.29
    pend
    2.22
    nell
    2.20
    land
    2.19
    NEY
    2.16
    ணு
    2.09
    rs
    2.08
    lands
    2.07
    tion
    2.07
    Activations Density 0.004%

    No Known Activations