© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129300
    Prev
    Next
    INDEX
    Explanations

    Liga and Vida 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
    潆
    -3.09
    ୌ
    -2.84
    icoot
    -2.70
    〤
    -2.66
    后感
    -2.61
    韪
    -2.61
     مناط
    -2.59
    神
    -2.58
    笈
    -2.53
    ikusbot
    -2.52
    POSITIVE LOGITS
    琑
    2.77
    to
    2.67
     {
    2.63
     
    2.59
            
    2.50
    いた
    2.41
    想
    2.38
    I
    2.36
    ゆく
    2.36
    section
    2.36
    Activations Density 0.006%

    No Known Activations