© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9373
    Prev
    Next
    INDEX
    Explanations

    math and greek letters

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

    mathematical symbols and variables

    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_40_width_16k_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
     достой
    0.59
     हितों
    0.54
    逊
    0.53
    踪
    0.52
    赚钱
    0.52
    宾
    0.51
     конкурса
    0.51
    newName
    0.51
    谋
    0.51
     무엇
    0.50
    POSITIVE LOGITS
     epsilon
    0.96
    theta
    0.95
     phi
    0.93
     Equation
    0.92
     theta
    0.92
     omega
    0.88
     Psi
    0.87
     Phi
    0.86
     equation
    0.86
     rho
    0.86
    Activations Density 0.018%

    No Known Activations