© 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. 74344
    Prev
    Next
    INDEX
    Explanations

    lists of items or stages

    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
     mainly
    -1.63
     most
    -1.59
     has
    -1.49
     these
    -1.47
     also
    -1.46
     especially
    -1.46
     an
    -1.44
     allerdings
    -1.43
     should
    -1.41
     probably
    -1.38
    POSITIVE LOGITS
    鸲
    1.59
    
    1.58
     教程
    1.46
    ⚥
    1.45
     pompe
    1.39
     DIFFERENT
    1.39
     Dinas
    1.38
     différents
    1.38
    伢
    1.36
     Spanyol
    1.35
    Activations Density 0.115%

    No Known Activations