© 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. 34-GEMMASCOPE-RES-131K
    7. 59497
    Prev
    Next
    INDEX
    Explanations

    universality class

    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_34/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
    ceptors
    -0.84
    hri
    -0.76
     tutors
    -0.75
     ویکی‌آمباردا
    -0.70
    ちな
    -0.68
    казания
    -0.68
    cave
    -0.68
    став
    -0.68
     карьер
    -0.66
    arium
    -0.66
    POSITIVE LOGITS
     class
    4.63
     classes
    3.81
    class
    3.44
    クラス
    2.92
     classe
    2.80
     Class
    2.69
    Class
    2.61
    classes
    2.59
     clase
    2.53
     className
    2.52
    Activations Density 0.280%

    No Known Activations