© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 10761
    Prev
    Next
    INDEX
    Explanations

    avoid or prohibitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Такая
    0.71
    呢
    0.70
    正好
    0.70
    archical
    0.66
    齊
    0.66
     taraf
    0.65
    嶄
    0.64
     ы
    0.64
     règ
    0.64
    ቻል
    0.64
    POSITIVE LOGITS
    Avoid
    3.28
     Avoid
    3.21
     avoid
    3.20
    avoid
    2.96
    不要
    2.89
     avoiding
    2.69
     avoided
    2.67
     jangan
    2.66
    避免
    2.63
     不要
    2.58
    Activations Density 0.554%

    No Known Activations