© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 156214
    Prev
    Next
    INDEX
    Explanations

    corresponding to

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

    movement, creation, transit, recreation

    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
     {
    0.49
     Eur
    0.48
     Tips
    0.44
     Matrix
    0.44
     Cafe
    0.44
     Vendor
    0.44
    dbjc
    0.44
     Boundaries
    0.43
     скло
    0.43
     Than
    0.43
    POSITIVE LOGITS
     healthful
    0.49
    示
    0.48
    यद
    0.47
     ಎಂಬುದ
    0.46
     outrageous
    0.45
    綽
    0.45
    ជា
    0.44
    鴻
    0.44
    穏
    0.43
    ето
    0.43
    Activations Density 0.000%

    No Known Activations