© 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. 56031
    Prev
    Next
    INDEX
    Explanations

    programming language syntax and keywords

    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
    جمة
    -0.77
    ЗИ
    -0.76
     tries
    -0.76
     after
    -0.74
     until
    -0.69
     Soon
    -0.69
     provides
    -0.69
    after
    -0.69
    Soon
    -0.68
    After
    -0.67
    POSITIVE LOGITS
    Translatef
    0.92
    ﻷ
    0.88
    anh
    0.84
    ellee
    0.83
    ghi
    0.80
    hspace
    0.79
     foss
    0.79
    ENOS
    0.78
     محف
    0.75
     flicker
    0.73
    Activations Density 0.001%

    No Known Activations