© 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. 31-GEMMASCOPE-2-RES-262K
    7. 1233
    Prev
    Next
    INDEX
    Explanations

    programming language import statements

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     și
    0.49
     và
    0.43
     dgn
    0.43
    ActionPerformed
    0.42
    และ
    0.41
     и
    0.41
     අපි
    0.40
     Nationalist
    0.40
    ajući
    0.40
     Popup
    0.39
    POSITIVE LOGITS
     wert
    0.41
     évent
    0.39
     тре
    0.38
    وم
    0.38
    يف
    0.38
    เวอร์
    0.37
    ളാ
    0.36
    é
    0.36
     custo
    0.36
    基本上
    0.36
    Activations Density 0.004%

    No Known Activations