© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 75718
    Prev
    Next
    INDEX
    Explanations

    reliably ejects

    np_acts-logits-general · gemini-2.5-flash-lite

    preventing immediate harm, future shortages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     हालात
    0.49
    ઓ
    0.47
    군
    0.47
    ussian
    0.46
    ವರ
    0.46
    কার্য
    0.45
    <em>
    0.44
    教育
    0.44
    𝔦
    0.44
    学校
    0.43
    POSITIVE LOGITS
    ..");
    0.50
     SALE
    0.47
    ాప
    0.46
     kebakaran
    0.46
     বিক্রয়
    0.45
     STILL
    0.45
     sale
    0.45
    شة
    0.44
     صف
    0.44
     coopération
    0.44
    Activations Density 0.000%

    No Known Activations