© 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. 81388
    Prev
    Next
    INDEX
    Explanations

    android widget or layout definitions

    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
    -0.88
    select
    -0.86
     heyday
    -0.81
    泡沫
    -0.81
     Wendy
    -0.80
    ylem
    -0.78
    ラックス
    -0.78
    📨
    -0.76
    kształ
    -0.74
     szabály
    -0.74
    POSITIVE LOGITS
    調査
    0.73
    Spinner
    0.72
     Spinner
    0.70
    🌶
    0.69
     intruder
    0.68
    因素
    0.68
    ichord
    0.67
    ueur
    0.66
     spinner
    0.66
    ？　
    0.66
    Activations Density 0.007%

    No Known Activations