© 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. 11882
    Prev
    Next
    INDEX
    Explanations

    commonly known as

    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
     such
    -1.52
     amikor
    -1.43
    得意
    -1.27
     
    -1.27
     they
    -1.27
    hibits
    -1.25
     up
    -1.25
     others
    -1.24
    々木
    -1.24
     apparently
    -1.23
    POSITIVE LOGITS
     their
    1.56
     間取り
    1.55
    年から
    1.52
    他們的
    1.47
    自己的
    1.45
    𖤣
    1.44
     摄影
    1.43
    お楽しみに
    1.41
    他们的
    1.39
    两人的
    1.39
    Activations Density 0.049%

    No Known Activations