© 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. 84450
    Prev
    Next
    INDEX
    Explanations

    days of the week

    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
     will
    -1.75
     or
    -1.66
    s
    -1.65
     -
    -1.64
     then
    -1.63
     which
    -1.62
    和
    -1.59
     was
    -1.58
     etc
    -1.57
     how
    -1.55
    POSITIVE LOGITS
     diminuer
    1.62
     siè
    1.61
     великолеп
    1.55
     douleurs
    1.52
     fidé
    1.48
    bánh
    1.45
     espé
    1.41
    
    1.41
    »?
    1.40
     ľah
    1.39
    Activations Density 0.029%

    No Known Activations