© 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. 38564
    Prev
    Next
    INDEX
    Explanations

    numbers and titles

    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
    Դ
    -0.88
    =("
    -0.77
    ﾛ
    -0.77
    .,
    -0.76
     jedenfalls
    -0.76
    raged
    -0.75
     сове
    -0.75
     мать
    -0.75
     цветами
    -0.74
     reagents
    -0.73
    POSITIVE LOGITS
    annulation
    0.90
     vorhand
    0.82
     stehenden
    0.81
     garantis
    0.81
    お昼
    0.79
     rất
    0.78
     angebra
    0.77
     ruidos
    0.77
    bebasan
    0.76
     légèrement
    0.75
    Activations Density 0.004%

    No Known Activations