© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 127378
    Prev
    Next
    INDEX
    Explanations

    decoupling, coupling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (--
    0.49
     '{
    0.48
     অথবা
    0.45
    ⚛
    0.45
    或
    0.45
     [['
    0.45
     事業
    0.43
    埋
    0.43
     участи
    0.43
     [-
    0.42
    POSITIVE LOGITS
     فراہم
    0.48
     notion
    0.43
     prospective
    0.43
    दाश्त
    0.41
    ちゃう
    0.39
     predicament
    0.39
     parlor
    0.39
     tentative
    0.39
     رکھتے
    0.38
    erebbe
    0.38
    Activations Density 0.007%

    No Known Activations