© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69436
    Prev
    Next
    INDEX
    Explanations

    uniform followed by programming terms

    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
    軾
    -1.62
     capucha
    -1.61
    いしい
    -1.46
    长的
    -1.44
     история
    -1.43
     attic
    -1.41
    𐑂
    -1.41
     geladeira
    -1.38
     gute
    -1.34
    водов
    -1.34
    POSITIVE LOGITS
    缐
    1.43
    أة
    1.42
    uniforms
    1.42
    傒
    1.33
     назва
    1.31
     caseros
    1.31
    UniformLocation
    1.30
    EndInit
    1.28
     about
    1.27
     including
    1.27
    Activations Density 0.010%

    No Known Activations