© 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. 129415
    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
     તમામ
    -0.08
     جميع
    -0.08
     모든
    -0.08
     all
    -0.08
     wszystkich
    -0.08
     όλ
    -0.08
     всех
    -0.08
     تمامی
    -0.07
     hiçbir
    -0.07
    ?!"
    -0.07
    POSITIVE LOGITS
     spawning
    0.06
     אַ
    0.06
    eous
    0.06
    ------
    0.05
    কর্ত
    0.05
     capricious
    0.05
     advocacy
    0.05
    ----
    0.05
    Partners
    0.05
     brewing
    0.05
    Activations Density 0.000%

    No Known Activations