© 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. 19834
    Prev
    Next
    INDEX
    Explanations

    programming code structures

    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
     will
    -2.05
     or
    -1.58
    Many
    -1.54
     with
    -1.48
    Numerous
    -1.45
    replyreport
    -1.41
    骨折
    -1.41
     and
    -1.41
     tendremos
    -1.40
     tendrás
    -1.37
    POSITIVE LOGITS
     that
    1.91
     such
    1.66
     suoi
    1.59
     his
    1.53
     lorsqu
    1.41
     AGENDA
    1.41
     ';
    1.38
     Memoir
    1.38
     planific
    1.36
    
    1.34
    Activations Density 0.016%

    No Known Activations