© 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. 10141
    Prev
    Next
    INDEX
    Explanations

    violence and harmful content

    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
     circum
    2.45
    wreck
    2.35
    కాల
    2.35
    roic
    2.26
    িমূলক
    2.26
    lik
    2.14
    rolled
    2.12
     fixed
    2.10
    廂
    2.09
    zahlung
    2.07
    POSITIVE LOGITS
    ом
    2.45
    ₮
    2.29
    erve
    2.26
    ۷
    2.25
    ۱
    2.18
    uyorum
    2.16
    unuz
    2.16
     ше
    2.12
    꾼
    2.08
    ోతి
    2.04
    Activations Density 0.031%

    No Known Activations