© 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. 119986
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    logging
    -0.06
    ut
    -0.06
    몇
    -0.06
    enje
    -0.06
     их
    -0.06
     basically
    -0.06
    Their
    -0.06
    Basically
    -0.06
     
    -0.06
     their
    -0.05
    POSITIVE LOGITS
     obter
    0.08
     alcuna
    0.07
    あらゆる
    0.07
     শুধুমাত্র
    0.06
     considers
    0.06
     accommodates
    0.06
     manter
    0.06
     фараз
    0.06
     powodu
    0.06
     كافة
    0.06
    Activations Density 0.000%

    No Known Activations