© 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. 207299
    Prev
    Next
    INDEX
    Explanations

    flight attendantsweet and sourupon particular occasionsan article

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

    software and plotting

    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
     filoz
    0.48
    ו
    0.46
    itiv
    0.44
    urali
    0.44
    etheus
    0.44
    idenza
    0.44
     filtra
    0.44
    PanelVisual
    0.43
    า
    0.43
    대로
    0.42
    POSITIVE LOGITS
     kiri
    0.45
     amn
    0.44
     surviving
    0.44
     губерна
    0.44
     ⿰
    0.43
     hợp
    0.42
     Hongkong
    0.42
     tại
    0.41
     survives
    0.41
     এইরূপ
    0.41
    Activations Density 0.001%

    No Known Activations