© 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. 43727
    Prev
    Next
    INDEX
    Explanations

    contrast or comparison

    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
     precisar
    -1.63
    
    -1.58
    哢
    -1.57
     averiguar
    -1.55
    屿
    -1.54
    ㌧
    -1.54
     además
    -1.53
    𝔗
    -1.53
     cuando
    -1.47
    行者
    -1.45
    POSITIVE LOGITS
    i
    1.72
     feiert
    1.62
    iI
    1.59
    Of
    1.58
    那个人
    1.55
     Produkten
    1.54
    1.53
    謦
    1.52
     說
    1.50
    pecabe
    1.49
    Activations Density 0.033%

    No Known Activations