© 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. 86197
    Prev
    Next
    INDEX
    Explanations

    comprehension and shortcomings

    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
    
    -2.91
     were
    -2.70
    纛
    -2.66
    苼
    -2.50
     philosophie
    -2.50
     didnt
    -2.48
    琑
    -2.45
    ↑↑↑</
    -2.44
    璠
    -2.39
    ſſel
    -2.38
    POSITIVE LOGITS
    1
    2.56
     {
    2.34
    {
    2.31
    や
    2.31
    colgante
    2.30
    或
    2.28
     که
    2.22
    鶲
    2.22
    ANNE
    2.17
     revamp
    2.11
    Activations Density 0.001%

    No Known Activations