© 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. 751
    Prev
    Next
    INDEX
    Explanations

    future saline technology metabolism

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

    analyzed with, we explore, lead to

    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
    袜子
    0.59
    鹑
    0.56
    리가
    0.55
    褛
    0.55
    锺
    0.55
     시절
    0.54
    mayın
    0.54
    侪
    0.54
    鲔
    0.54
     завтра
    0.53
    POSITIVE LOGITS
    Ⅰ
    0.78
    Ⅲ
    0.66
     gradually
    0.65
    Ⅱ
    0.64
     丨
    0.63
    arrerol
    0.63
    Ⅴ
    0.61
    
    0.61
    Ｒ
    0.59
     firstly
    0.59
    Activations Density 0.050%

    No Known Activations