© 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. 1475
    Prev
    Next
    INDEX
    Explanations

    spacetime physics theories

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

    theoretical physics and relativity

    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
     финансо
    0.85
    的价格
    0.77
    赌场
    0.77
    赛事
    0.77
    <unused27>
    0.76
     фестива
    0.75
     satış
    0.75
     المالية
    0.75
    电视台
    0.75
    🏦
    0.75
    POSITIVE LOGITS
     spacetime
    1.11
     physics
    1.08
     massless
    1.08
     Dirac
    1.02
     symmetries
    0.98
     scalar
    0.98
     tensor
    0.96
     dynamical
    0.96
     cosmological
    0.95
     antisymmetric
    0.95
    Activations Density 0.017%

    No Known Activations