© 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. 73827
    Prev
    Next
    INDEX
    Explanations

    if/else conditions or comparisons

    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
     artık
    -0.88
     fortfarande
    -0.85
     trimestre
    -0.84
    СО
    -0.83
     that
    -0.82
     Historie
    -0.79
     now
    -0.78
    XFF
    -0.78
     också
    -0.77
    那
    -0.75
    POSITIVE LOGITS
     same
    0.92
     equal
    0.91
    isSame
    0.89
     virtù
    0.89
    相同
    0.88
     molti
    0.87
     if
    0.85
     riten
    0.85
     iguales
    0.85
     égal
    0.84
    Activations Density 0.003%

    No Known Activations