© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11781
    Prev
    Next
    INDEX
    Explanations

    words starting with "Squ"

    np_acts-logits-general · gemini-2.5-flash-lite

    square root, sqinn, Squirtle, Squa

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inap
    0.40
    umar
    0.39
    ymen
    0.39
    csr
    0.39
    台
    0.39
    convex
    0.38
    上有
    0.38
    凸
    0.38
     cooldown
    0.38
     CPM
    0.37
    POSITIVE LOGITS
    Squ
    0.98
     squ
    0.96
     Squ
    0.95
     SQ
    0.89
    squ
    0.87
     Squire
    0.83
     Sq
    0.81
     sq
    0.80
    Sq
    0.77
     squire
    0.73
    Activations Density 0.053%

    No Known Activations