© 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. 64592
    Prev
    Next
    INDEX
    Explanations

    going to / gonna constructions

    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
     mogen
    -1.01
    便利です
    -0.95
    こちらは
    -0.87
    他說
    -0.84
     konnten
    -0.84
     helpt
    -0.83
    GO
    -0.82
    骉
    -0.79
    他说
    -0.79
     solches
    -0.78
    POSITIVE LOGITS
     gonna
    4.81
     going
    4.44
    gonna
    2.95
    Gonna
    2.91
     will
    2.64
     Gonna
    2.59
     GONNA
    2.34
    Going
    2.09
    going
    2.02
     буде
    1.95
    Activations Density 0.080%

    No Known Activations