© 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. 119260
    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
     cause
    -0.06
     ``
    -0.06
     několik
    -0.06
     couro
    -0.05
     যায়
    -0.05
    टकों
    -0.05
     us
    -0.05
     trig
    -0.05
     pratis
    -0.05
     wielu
    -0.05
    POSITIVE LOGITS
    ೊಂದಿಗೆ
    0.07
     with
    0.06
    MenuActive
    0.06
     никакой
    0.06
    続いて
    0.06
    嘅
    0.06
     mostly
    0.06
    ჷ
    0.06
    mostly
    0.06
     ника
    0.06
    Activations Density 0.000%

    No Known Activations