© 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-16K
    7. 12612
    Prev
    Next
    INDEX
    Explanations

    code delimiters

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    imide
    0.38
    者が
    0.36
     制
    0.35
     ус
    0.34
    ClInclude
    0.34
    制
    0.34
    ㄱ
    0.34
    𝚐
    0.34
    <unused80>
    0.33
    Pd
    0.33
    POSITIVE LOGITS
    失望
    0.41
     riche
    0.38
     الاحت
    0.38
     disappointment
    0.37
    ächst
    0.36
    uwa
    0.35
    ádza
    0.35
     الموا
    0.35
     dissatisfaction
    0.35
     والله
    0.34
    Activations Density 0.253%

    No Known Activations