© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73275
    Prev
    Next
    INDEX
    Explanations

    UIColor and UIImage initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </strong>
    -2.80
    </h3>
    -2.45
    蹀
    -2.27
    呖
    -2.16
    作って
    -2.06
    坼
    -2.05
    ayaquil
    -2.03
    .’”
    -2.02
    <td>
    -1.98
    潆
    -1.98
    POSITIVE LOGITS
    *
    2.23
    '
    2.06
     套装
    1.91
    媼
    1.84
     语
    1.83
     móds
    1.80
     stratég
    1.79
    tienen
    1.78
     UIColor
    1.76
    {
    1.75
    Activations Density 0.003%

    No Known Activations