© 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. 61003
    Prev
    Next
    INDEX
    Explanations

    mathematical integration and quadrature

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

    mathematical integration and calculus

    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
     البنات
    0.51
     डेयरी
    0.50
    传染
    0.46
    婕
    0.45
    谴
    0.45
     chuyện
    0.44
    🏩
    0.43
    ⇰
    0.43
    设计师
    0.42
     hôtel
    0.42
    POSITIVE LOGITS
     integrals
    0.76
     integrand
    0.73
     ∫
    0.64
    积分
    0.63
    積分
    0.62
    Integr
    0.58
     Integrate
    0.56
     integrator
    0.55
    Riemann
    0.55
     Integr
    0.54
    Activations Density 0.017%

    No Known Activations