© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3099
    Prev
    Next
    INDEX
    Explanations

    enduring stress and load

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
     dots
    1.76
    憑
    1.73
     cancel
    1.71
    另
    1.70
     refund
    1.64
     vende
    1.64
     確認
    1.59
    惜
    1.56
     Refund
    1.56
    提示
    1.55
    POSITIVE LOGITS
     withstood
    1.44
     ambientes
    1.35
    荷重
    1.31
     abuse
    1.25
     użyt
    1.23
     нагрузки
    1.23
     subjected
    1.22
     Abuse
    1.21
     abused
    1.16
    ethoven
    1.15
    Activations Density 0.365%

    No Known Activations