© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117237
    Prev
    Next
    INDEX
    Explanations

    hypothetical statements with "would"

    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
     когда
    -2.23
     when
    -2.23
     cuando
    -2.02
     quando
    -1.91
     will
    -1.52
     när
    -1.50
     जब
    -1.48
    的时候
    -1.47
     lorsque
    -1.45
     عندما
    -1.44
    POSITIVE LOGITS
     would
    3.11
     if
    2.31
     gdyby
    2.30
    Would
    2.27
    would
    2.03
     wouldnt
    2.00
     wouldn
    1.85
     Would
    1.71
     olisi
    1.70
     hypothetical
    1.70
    Activations Density 0.076%

    No Known Activations