© 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. 248578
    Prev
    Next
    INDEX
    Explanations

    common word pairings

    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
     ngừng
    0.50
    踞
    0.49
    aság
    0.48
     создание
    0.48
     المعادلات
    0.47
    ОВА
    0.46
    ކ
    0.46
    énération
    0.46
     створення
    0.45
     પડ
    0.45
    POSITIVE LOGITS
     (
    0.55
     Nikon
    0.51
     distributors
    0.50
     doped
    0.50
     mitt
    0.49
     eff
    0.49
     anyone
    0.49
     nitrile
    0.49
     three
    0.49
     cinnamon
    0.48
    Activations Density 0.000%

    No Known Activations