© 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. 199016
    Prev
    Next
    INDEX
    Explanations

    Russian, Turkish, Vietnamese, Spanish, Lao, Turkish

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

    explanation of relativity

    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
    الق
    0.59
    Davidson
    0.48
    伉
    0.47
    口座
    0.47
    straction
    0.46
    בש
    0.46
    ᅯ
    0.46
    ースト
    0.46
    恈
    0.46
    QCD
    0.46
    POSITIVE LOGITS
     Э
    0.50
     magar
    0.48
    an
    0.48
     новый
    0.47
    ta
    0.47
     ຊ
    0.47
     şirket
    0.45
     başarılı
    0.45
     chờ
    0.45
     falta
    0.45
    Activations Density 0.000%

    No Known Activations