© 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. 22-GEMMASCOPE-RES-131K
    7. 130628
    Prev
    Next
    INDEX
    Explanations

    epsilon, numbers, symbols

    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_22/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
     saiu
    -0.99
    cile
    -0.93
     actualmente
    -0.90
     buses
    -0.90
     cowok
    -0.85
    。「
    -0.83
    meuble
    -0.83
     ""
    -0.82
     \"
    -0.81
    CDD
    -0.81
    POSITIVE LOGITS
    Как
    0.96
     its
    0.93
    {?>
    0.91
    وال
    0.85
     می‌گو
    0.85
    一样的
    0.84
    accéder
    0.83
    acjach
    0.83
     kurtka
    0.81
    ATHERINE
    0.79
    Activations Density 0.049%

    No Known Activations