© 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. 129295
    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
     появляется
    -0.07
    增加
    -0.06
     szybko
    -0.06
     whilst
    -0.06
     улуч
    -0.06
    eah
    -0.05
     siempre
    -0.05
     any
    -0.05
     improvements
    -0.05
     дене
    -0.05
    POSITIVE LOGITS
     cuja
    0.06
    ászló
    0.06
     marvelous
    0.06
     breathtaking
    0.06
    🐶
    0.06
     gorgeous
    0.06
     $(*
    0.06
    vare
    0.06
    havior
    0.06
     restrained
    0.06
    Activations Density 0.000%

    No Known Activations