© 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. 128333
    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
     so
    -0.06
    زه
    -0.06
     كذلك
    -0.06
     orig
    -0.06
    ziała
    -0.06
    、
    -0.06
     dále
    -0.06
    ･･･
    -0.06
     সমাবে
    -0.06
     جمعه
    -0.05
    POSITIVE LOGITS
     you
    0.08
    తులను
    0.06
     können
    0.06
     could
    0.06
     Curved
    0.06
     아무
    0.06
    kant
    0.06
    চো
    0.06
     wirst
    0.06
     herkes
    0.06
    Activations Density 0.000%

    No Known Activations