© 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
    2. Gemma-3-27B
    3. 40-GEMMASCOPE-2-RES-16K
    4. 9780
    Prev
    Next
    INDEX
    Explanations

    GPU graphics shaders

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

    graphics shaders and OpenGL

    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
    hô
    0.45
    ristown
    0.42
    гы
    0.41
     diken
    0.41
     思い
    0.41
    ローチ
    0.41
    鹹
    0.40
    ydia
    0.40
    ၜ
    0.39
     Welles
    0.39
    POSITIVE LOGITS
     Shader
    1.24
     shader
    1.23
    Shader
    1.20
    shader
    1.18
    GLuint
    1.16
     shaders
    1.12
     GL
    1.04
    glBind
    1.03
     OpenGL
    1.02
    shaders
    1.02
    Activations Density 0.032%

    No Known Activations