© 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. 147544
    Prev
    Next
    INDEX
    Explanations

    "Strict Transport Security" or "job site"

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

    legal persona complexity

    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
    л
    0.57
    糈
    0.57
     পূরণ
    0.54
    ผ้า
    0.54
    Courses
    0.52
    㥳
    0.52
    iał
    0.51
    檤
    0.51
    氶
    0.50
    壃
    0.50
    POSITIVE LOGITS
     precipit
    0.53
     contention
    0.47
     manipulation
    0.47
    "
    0.45
    قات
    0.45
     manipulative
    0.44
     interrog
    0.44
    ッター
    0.44
    ंका
    0.43
     marketing
    0.42
    Activations Density 0.001%

    No Known Activations