© 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. 12045
    Prev
    Next
    INDEX
    Explanations

    but, if, slightly, was

    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
     poissons
    -1.05
     nawet
    -1.01
    INCLUDES
    -0.99
     alls
    -0.98
     рассматри
    -0.98
     boe
    -0.98
    ⿸
    -0.98
     bahkan
    -0.97
     andes
    -0.97
     bénévol
    -0.95
    POSITIVE LOGITS
     slightly
    1.96
     could
    1.91
     немного
    1.87
     hơi
    1.83
     biraz
    1.78
    有点
    1.73
     etwas
    1.68
    有些
    1.67
    有點
    1.59
     sometimes
    1.58
    Activations Density 0.044%

    No Known Activations