© 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. 119959
    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
     опять
    -0.08
     novamente
    -0.07
    旗下
    -0.06
     nuevamente
    -0.06
     wollen
    -0.06
     biraz
    -0.06
     yaptığı
    -0.06
     मशहूर
    -0.06
    Again
    -0.06
     आढ
    -0.06
    POSITIVE LOGITS
     envy
    0.06
     sadness
    0.06
     until
    0.06
     parting
    0.06
     Distress
    0.06
     وم
    0.06
     እየ
    0.06
    भग
    0.06
     expiring
    0.06
    until
    0.05
    Activations Density 0.009%

    No Known Activations