© 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. 25816
    Prev
    Next
    INDEX
    Explanations

    for loop structures

    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
     their
    -1.05
    긍
    -1.02
    elux
    -0.93
     役
    -0.84
     Кроме
    -0.82
    énagement
    -0.82
    łasz
    -0.81
     Karaoke
    -0.81
    weich
    -0.79
     είναι
    -0.77
    POSITIVE LOGITS
    int
    1.04
     int
    0.91
    zetek
    0.77
     Tonight
    0.76
     sabia
    0.74
     кръ
    0.74
    Итог
    0.73
    rigado
    0.73
    上品
    0.72
    看你
    0.71
    Activations Density 0.008%

    No Known Activations