© 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. 129429
    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
     типу
    -0.06
     principally
    -0.06
     in
    -0.06
     صعب
    -0.06
     главным
    -0.06
    ='')
    -0.06
     लगाकर
    -0.06
    forcements
    -0.06
     catchy
    -0.06
     పరిస్థ
    -0.06
    POSITIVE LOGITS
    Despite
    0.06
    despite
    0.06
     HAVE
    0.06
     spite
    0.06
     contrairement
    0.06
    Peace
    0.06
     blanche
    0.05
     malgré
    0.05
     رغم
    0.05
    jala
    0.05
    Activations Density 0.000%

    No Known Activations