© 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. 120102
    Prev
    Next
    INDEX
    Explanations

    invention relates to

    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
    доступ
    -0.06
     acess
    -0.06
     budgeted
    -0.06
    erry
    -0.06
     augment
    -0.05
     attain
    -0.05
     राशन
    -0.05
     acces
    -0.05
     ချ
    -0.05
     використання
    -0.05
    POSITIVE LOGITS
     хло
    0.06
     پدر
    0.06
    acycl
    0.06
     ähn
    0.06
     جلوگیری
    0.06
     Gayatri
    0.06
    发起
    0.06
    想要
    0.06
    ٽ
    0.06
     zugleich
    0.06
    Activations Density 0.001%

    No Known Activations