© 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. 10719
    Prev
    Next
    INDEX
    Explanations

    to harm, to pass, to school

    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
     구성
    0.84
     и
    0.75
     ות
    0.74
    𝗽
    0.74
     बताऊंगा
    0.73
     упро
    0.73
     класи
    0.73
    }`));
    0.72
     направления
    0.72
    ąż
    0.72
    POSITIVE LOGITS
     dwells
    0.78
     standstill
    0.77
     grief
    0.74
     Республика
    0.70
     whirl
    0.70
     halt
    0.68
     resemble
    0.68
     ruin
    0.66
     sensing
    0.65
     obliquely
    0.65
    Activations Density 0.019%

    No Known Activations