© 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. 120374
    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
     у
    -0.08
    はお
    -0.07
    排行
    -0.06
     под
    -0.06
     edição
    -0.06
     초기
    -0.06
    额外
    -0.06
     około
    -0.06
    だけ
    -0.06
     до
    -0.06
    POSITIVE LOGITS
     football
    0.06
     geographically
    0.06
     combines
    0.06
     dismant
    0.05
     undermining
    0.05
     新
    0.05
     بال
    0.05
    ullin
    0.05
     对
    0.05
     mining
    0.05
    Activations Density 0.000%

    No Known Activations