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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 8512
    Prev
    Next
    INDEX
    Explanations

    spacetime, gravity, quantum physics

    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_40_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
    培训
    0.54
    deployRoot
    0.48
     Udemy
    0.48
    笞
    0.47
     уя
    0.47
    Carousel
    0.47
     instalação
    0.47
    🅻
    0.46
     менедж
    0.46
     комплект
    0.45
    POSITIVE LOGITS
     spacetime
    1.30
     cosmological
    1.04
     gravitational
    1.01
     gravitation
    0.90
     quantum
    0.89
     massless
    0.88
     curvature
    0.88
     gravity
    0.83
     cosmology
    0.83
     gravit
    0.80
    Activations Density 0.078%

    No Known Activations