© 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. 123955
    Prev
    Next
    INDEX
    Explanations

    links and official sounding terms

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

    history, benefits of administration

    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
     mieć
    0.49
     måste
    0.48
     प्रिपरेशन
    0.47
     mať
    0.47
     иметь
    0.46
     réalisé
    0.46
    姪
    0.46
     Kral
    0.45
     compilation
    0.45
    मेंट
    0.43
    POSITIVE LOGITS
    pano
    0.56
    kswagen
    0.50
    nese
    0.49
    l
    0.49
    hausen
    0.48
    lush
    0.48
    hk
    0.48
    actin
    0.48
    msen
    0.48
    lage
    0.47
    Activations Density 0.000%

    No Known Activations