© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 26145
    Prev
    Next
    INDEX
    Explanations

    policy and secretary roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Trimethyl
    0.56
     产品
    0.51
    苛
    0.44
     ব্যাঙ্ক
    0.43
    বার্গ
    0.43
    ຜະລິດຕະພັນ
    0.43
     tumeur
    0.42
    tLogRow
    0.42
    醪
    0.42
     aand
    0.42
    POSITIVE LOGITS
     Secretariat
    0.68
     secretariat
    0.63
     Secretary
    0.63
     secretary
    0.62
     Department
    0.58
     secretaries
    0.57
     policy
    0.57
     affairs
    0.57
     policym
    0.57
     Policy
    0.56
    Activations Density 0.002%

    No Known Activations