© 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. 130931
    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
    DbContext
    -0.07
     Telugu
    -0.06
     develops
    -0.06
     histo
    -0.06
     dangere
    -0.06
    subjects
    -0.06
    也被
    -0.06
    %);
    -0.06
     very
    -0.06
    فع
    -0.06
    POSITIVE LOGITS
    8
    0.06
     සහිත
    0.05
     außer
    0.05
     motivo
    0.05
     njegova
    0.05
    3
    0.05
     গুলোতে
    0.05
     reste
    0.05
     durumda
    0.05
     opposing
    0.05
    Activations Density 0.000%

    No Known Activations