© 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. 180285
    Prev
    Next
    INDEX
    Explanations

    collect the

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

    weight and definitions

    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
     в
    0.51
    ТО
    0.49
    ЕВ
    0.48
     contempl
    0.47
     первой
    0.47
     contemplated
    0.47
    ТР
    0.46
    лл
    0.45
     одним
    0.45
    т
    0.45
    POSITIVE LOGITS
    ാരോഗ്യ
    0.48
     dinh
    0.47
    ynet
    0.47
     Sunak
    0.45
     Murder
    0.45
     autosomal
    0.45
    han
    0.44
     मीनिंग
    0.44
    níku
    0.42
    yg
    0.42
    Activations Density 0.003%

    No Known Activations