© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9326
    Prev
    Next
    INDEX
    Explanations

    ruby and garnet gemstones

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

    ruby and its ecosystem

    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
    ᱣ
    0.42
     цере
    0.39
    ंपर्यंत
    0.39
    ahua
    0.39
    ȋ
    0.39
     Quakers
    0.38
    𝙚
    0.38
     करार
    0.38
     procédés
    0.38
    ⓓ
    0.37
    POSITIVE LOGITS
     Ruby
    1.02
     ruby
    1.01
    Ruby
    1.00
    ruby
    0.82
     rub
    0.78
    RUB
    0.76
     garnet
    0.75
     gem
    0.74
    Rub
    0.72
     gems
    0.71
    Activations Density 0.030%

    No Known Activations