© 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. 45591
    Prev
    Next
    INDEX
    Explanations

    words starting with squ

    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
    竪
    -0.80
    udessa
    -0.77
     Größen
    -0.73
    邇
    -0.72
     collect
    -0.72
     original
    -0.72
     Scheiben
    -0.72
     p
    -0.72
    yyyy
    -0.71
     шах
    -0.71
    POSITIVE LOGITS
     squ
    2.61
     Squ
    2.38
    Squ
    2.36
    squ
    2.31
     SQ
    1.95
     SQU
    1.94
    SQU
    1.83
     sq
    1.75
     Sq
    1.69
    SQ
    1.64
    Activations Density 0.018%

    No Known Activations