© 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. 225403
    Prev
    Next
    INDEX
    Explanations

    unless no

    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
    x
    0.63
     Property
    0.52
     Airlines
    0.51
     Commodities
    0.49
    y
    0.49
     Pipeline
    0.47
     apartheid
    0.46
    heli
    0.46
     Industry
    0.45
     +
    0.45
    POSITIVE LOGITS
    sebastian
    0.56
     シル
    0.52
     аргу
    0.50
    ሐ
    0.49
     stwier
    0.48
     cultivés
    0.46
    伊
    0.46
    ですが
    0.46
     ඉක්
    0.46
    ✾
    0.46
    Activations Density 0.001%

    No Known Activations