© 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. 119587
    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
     является
    -0.06
     нового
    -0.06
     possesses
    -0.06
    easter
    -0.06
     owns
    -0.06
    parsing
    -0.06
     νέ
    -0.06
     clang
    -0.06
    fragments
    -0.06
    などの
    -0.06
    POSITIVE LOGITS
     کوشش
    0.06
     저희
    0.06
     essayer
    0.06
    เขา
    0.06
     непосредственно
    0.06
    Our
    0.06
     försö
    0.06
    :
    0.06
     our
    0.06
     zelfs
    0.06
    Activations Density 0.000%

    No Known Activations