© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130031
    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
     ಒಳ್ಳೆಯ
    -0.08
    となっています
    -0.06
     ισ
    -0.06
    ことが多い
    -0.06
     чаще
    -0.06
     fonctionner
    -0.06
    vykor
    -0.06
    如下
    -0.06
     юм
    -0.06
     deel
    -0.06
    POSITIVE LOGITS
    、
    0.07
    never
    0.06
     out
    0.06
    Never
    0.06
     never
    0.06
    ,
    0.05
     seinem
    0.05
    Clearly
    0.05
     seemingly
    0.05
     статті
    0.05
    Activations Density 0.000%

    No Known Activations