© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120189
    Prev
    Next
    INDEX
    Explanations

    osmolarity and density

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     processor
    -0.07
     processors
    -0.07
     scientist
    -0.06
     നമു
    -0.06
     મુખ્ય
    -0.06
     engineers
    -0.06
     cardigan
    -0.06
     ఏడాది
    -0.06
     பொதுவாக
    -0.06
     towers
    -0.05
    POSITIVE LOGITS
     सत्यापित
    0.07
    ၈
    0.06
     daarmee
    0.06
    分辨
    0.06
     mới
    0.06
     zako
    0.06
    做
    0.06
    操作
    0.06
    เชื่อ
    0.06
    XII
    0.06
    Activations Density 0.005%

    No Known Activations