© 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. 2868
    Prev
    Next
    INDEX
    Explanations

    arrest or capture

    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
    Not in Any Lists

    No Comments

    Negative Logits
     উপে
    0.46
    监理
    0.43
    ustainability
    0.39
    医
    0.39
     সার্টিফি
    0.38
     અનુભ
    0.38
    忘
    0.38
     symptômes
    0.37
    ྨ
    0.37
     Explorer
    0.37
    POSITIVE LOGITS
     arrests
    1.74
     arrest
    1.63
    arrest
    1.51
     arrested
    1.48
    逮捕
    1.48
     Arrest
    1.38
     arresting
    1.29
     apprehended
    1.24
     गिरफ्तार
    1.23
     apprehend
    1.17
    Activations Density 0.011%

    No Known Activations