© 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. 43135
    Prev
    Next
    INDEX
    Explanations

    research context

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

    language nuances and style

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Анти
    0.59
    產品
    0.52
    Ι
    0.52
    ผลิตภัณฑ์
    0.51
    ˆ‚
    0.51
     Ін
    0.50
     एशिया
    0.50
     设备
    0.49
     দরিদ্র
    0.49
     кількість
    0.49
    POSITIVE LOGITS
     They
    0.49
     It
    0.48
    bl
    0.47
    ower
    0.46
    amatkan
    0.46
    b
    0.45
    ashion
    0.45
    bt
    0.43
     candle
    0.43
    aking
    0.42
    Activations Density 0.001%

    No Known Activations