© 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. 118552
    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
     from
    -0.09
     continue
    -0.07
    बाट
    -0.06
     redistribute
    -0.06
     the
    -0.06
     melanjutkan
    -0.06
    **************
    -0.06
     melancholy
    -0.06
     disgraceful
    -0.05
     ==========
    -0.05
    POSITIVE LOGITS
     Hỏi
    0.07
    ;
    0.07
    ริกา
    0.06
     নিয়োগ
    0.06
     ;
    0.06
     Лондон
    0.06
     plea
    0.06
     صحبت
    0.06
    很少
    0.06
     لازم
    0.06
    Activations Density 0.000%

    No Known Activations