© 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. 3
    Prev
    Next
    INDEX
    Explanations

    quoting when citing sources

    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
    撓
    -1.65
    ☫
    -1.59
        
    -1.58
    ernalia
    -1.57
    也没
    -1.56
          
    -1.55
    jestel
    -1.52
    焢
    -1.52
    риста
    -1.52
    ”)
    -1.52
    POSITIVE LOGITS
     the
    2.48
     bezw
    2.00
    atser
    1.93
    ݯ
    1.80
    guigu
    1.75
     OGSÅ
    1.71
    genodigd
    1.71
     Він
    1.69
    után
    1.68
     involucra
    1.67
    Activations Density 0.012%

    No Known Activations