© 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. 178341
    Prev
    Next
    INDEX
    Explanations

    working and jobs

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

    greetings and job contexts

    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
    려서
    0.50
     participle
    0.49
     సాహిత్య
    0.47
     способствует
    0.45
     సాహిత
    0.44
    っぷ
    0.44
    始める
    0.44
    ད
    0.44
    imach
    0.44
    ኘት
    0.43
    POSITIVE LOGITS
     slats
    0.51
    working
    0.48
     orders
    0.47
    orders
    0.46
    worker
    0.45
     jobs
    0.44
     Aiden
    0.44
     kids
    0.44
     Jobs
    0.44
    Jobs
    0.44
    Activations Density 0.000%

    No Known Activations