© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49472
    Prev
    Next
    INDEX
    Explanations

    while, now, early timings

    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
     após
    -1.17
     после
    -1.14
     après
    -1.13
     dopo
    -1.13
     after
    -1.10
     después
    -1.09
     לאחר
    -1.06
     після
    -1.02
     setelah
    -1.01
    Prior
    -0.99
    POSITIVE LOGITS
     while
    4.25
    while
    3.11
     mientras
    2.77
    While
    2.63
     enquanto
    2.61
     mentre
    2.56
     While
    2.47
     WHILE
    2.33
     whilst
    2.33
    趁
    2.23
    Activations Density 0.037%

    No Known Activations