© 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. 119909
    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
     నాయ
    -0.06
     করলো
    -0.06
     dwell
    -0.06
    ↵↵
    -0.06
    裡
    -0.06
     clichés
    -0.05
    从
    -0.05
    Philippe
    -0.05
     correspondences
    -0.05
     punishing
    -0.05
    POSITIVE LOGITS
     and
    0.07
     хоть
    0.06
     amd
    0.06
     পরই
    0.06
     bara
    0.06
     meskipun
    0.06
     Though
    0.06
     અને
    0.06
     despite
    0.06
     qualsiasi
    0.06
    Activations Density 0.000%

    No Known Activations