© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12385
    Prev
    Next
    INDEX
    Explanations

    while and concurrent actions

    np_acts-logits-general · gemini-2.5-flash-lite

    simultaneous actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    اً
    0.62
     밝혔
    0.62
    in
    0.61
     giornata
    0.61
     photometric
    0.61
    ना
    0.59
     January
    0.59
     pierwsze
    0.57
    ن
    0.57
    when
    0.57
    POSITIVE LOGITS
    Mientras
    0.89
     terwijl
    0.82
     while
    0.80
     Mientras
    0.80
     동시에
    0.80
     While
    0.79
     gleichzeitig
    0.78
     enquanto
    0.73
     Simultaneously
    0.73
     simultaneously
    0.71
    Activations Density 0.256%

    No Known Activations