© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8262
    Prev
    Next
    INDEX
    Explanations

    official documents and legal filings

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

    document metadata: date, name, version

    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_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    arakat
    0.42
     約
    0.42
    adple
    0.42
    ›
    0.41
    ▷
    0.41
    早在
    0.41
     viện
    0.40
     উপমহাদেশ
    0.40
    Congrats
    0.40
     ছাত্রদের
    0.40
    POSITIVE LOGITS
     Date
    0.44
     NOTICE
    0.43
    Date
    0.41
    $=\
    0.40
     Instructions
    0.40
     Dated
    0.40
     Name
    0.40
     instructions
    0.39
    Dated
    0.39
    DATE
    0.38
    Activations Density 0.027%

    No Known Activations