© 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. 31-GEMMASCOPE-2-RES-262K
    4. 95299
    Prev
    Next
    INDEX
    Explanations

    describing colors and brightness

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

    vibrant and colorful descriptions

    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
     intim
    0.57
     oliv
    0.52
     in
    0.51
     oak
    0.51
     monospace
    0.49
     रजत
    0.48
     kū
    0.48
    🩶
    0.47
    grey
    0.46
    leather
    0.46
    POSITIVE LOGITS
     colorful
    1.20
    Colorful
    1.16
    colorful
    1.16
     Colorful
    1.09
    彩
    1.09
     colorido
    1.08
     colourful
    1.05
    彩色
    1.01
    色彩
    0.98
     couleurs
    0.94
    Activations Density 0.202%

    No Known Activations