© 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. 21859
    Prev
    Next
    INDEX
    Explanations

    compiler

    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
     bandits
    0.50
    马拉
    0.48
     রেলপথ
    0.44
     hammock
    0.44
     బ్రిటిష్
    0.43
    చ్
    0.43
     ハンドバッグ
    0.43
    ші
    0.42
    ｮ
    0.42
     টেলিগ্রাফ
    0.42
    POSITIVE LOGITS
    javac
    0.72
     javac
    0.64
     JDK
    0.55
    JDK
    0.53
    Compiler
    0.53
     enzymes
    0.52
    java
    0.50
     Enzymes
    0.49
    projectlombok
    0.49
    output
    0.48
    Activations Density 0.011%

    No Known Activations