© 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. 34-GEMMASCOPE-RES-131K
    7. 2017
    Prev
    Next
    INDEX
    Explanations

    conditionals starting 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
     will
    -2.42
     can
    -1.39
     when
    -1.29
     Traditionally
    -1.19
     nantinya
    -1.14
     ће
    -1.10
     jeśli
    -1.09
     unusually
    -1.08
     although
    -1.05
     When
    -1.05
    POSITIVE LOGITS
     wouldn
    1.85
     would
    1.70
    wouldn
    1.48
     today
    1.38
     instead
    1.34
     serait
    1.30
    probably
    1.27
    Wouldn
    1.27
    Instead
    1.24
     wouldnt
    1.24
    Activations Density 0.030%

    No Known Activations