© 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. 34-GEMMASCOPE-RES-131K
    7. 103121
    Prev
    Next
    INDEX
    Explanations

    technical specification or code snippet

    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
     preguntas
    -0.81
    fillment
    -0.77
     involvement
    -0.76
     вкус
    -0.75
    altar
    -0.72
     الملك
    -0.71
     feline
    -0.71
    DetailComponent
    -0.71
    你不要
    -0.70
     Änderung
    -0.69
    POSITIVE LOGITS
    getCustomer
    0.81
     Tuan
    0.78
     　
    0.76
     resonances
    0.75
    щими
    0.72
     ки
    0.68
     harvested
    0.67
    eador
    0.65
    seman
    0.65
     thôi
    0.65
    Activations Density 0.020%

    No Known Activations