© 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. 48453
    Prev
    Next
    INDEX
    Explanations

    indexing, subsetting, accessing

    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
     After
    -1.99
     Following
    -1.58
     стоко
    -1.54
    -1.52
     using
    -1.52
    でしたが
    -1.52
    
    -1.50
     would
    -1.49
     waarom
    -1.49
    ቭ
    -1.46
    POSITIVE LOGITS
    ...
    1.93
    Thankfully
    1.91
    Fortunately
    1.85
    Luckily
    1.82
    ほんと
    1.79
    謌
    1.75
    s
    1.71
    鶿
    1.66
    　　-
    1.66
    個人的には
    1.66
    Activations Density 0.001%

    No Known Activations