© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6571
    Prev
    Next
    INDEX
    Explanations

    text effects, shaders, blur, gradients

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

    shaders, textures, rendering

    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_53_width_65k_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
    statements
    0.49
    俑
    0.49
    identification
    0.48
    セント
    0.46
     नौकर
    0.46
    enapi
    0.46
     przedsi
    0.45
    筺
    0.45
    囑
    0.44
     ofici
    0.43
    POSITIVE LOGITS
     blur
    1.46
     blurring
    1.43
     Blur
    1.39
     gradient
    1.36
     shader
    1.36
     blurred
    1.30
     Gradient
    1.30
     blurry
    1.27
     shaders
    1.27
    blur
    1.27
    Activations Density 0.099%

    No Known Activations