© 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. 120307
    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
     more
    -0.06
     an
    -0.06
     पूर्वानु
    -0.06
     achieve
    -0.06
     ihm
    -0.06
     take
    -0.06
     ebenso
    -0.06
    );
    -0.05
    Segment
    -0.05
    Crow
    -0.05
    POSITIVE LOGITS
     bản
    0.07
     epistem
    0.07
     vain
    0.06
    바
    0.06
    已經
    0.06
    rdoba
    0.06
    错误的
    0.06
    已经
    0.06
     ২
    0.06
    协议
    0.06
    Activations Density 0.000%

    No Known Activations