© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60424
    Prev
    Next
    INDEX
    Explanations

    extent of study

    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
    ائمة
    -0.85
     fű
    -0.77
     használ
    -0.77
     basado
    -0.76
    prueba
    -0.75
     tayo
    -0.75
    ühnen
    -0.75
     현
    -0.74
     χα
    -0.74
    onu
    -0.73
    POSITIVE LOGITS
     studied
    3.83
    studied
    3.08
     study
    2.84
    研究
    2.67
     investigated
    2.61
     studying
    2.56
     изу
    2.55
     research
    2.52
     researched
    2.47
     studies
    2.38
    Activations Density 0.264%

    No Known Activations