© 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. 119613
    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
     huidige
    -0.08
    current
    -0.08
    现在的
    -0.07
     현재
    -0.07
     वर्तमान
    -0.07
     until
    -0.07
     বর্তমান
    -0.07
     सध्या
    -0.07
     current
    -0.07
    currently
    -0.07
    POSITIVE LOGITS
     लड़कियों
    0.06
     disconcert
    0.06
     immedi
    0.06
     publicó
    0.05
     दिलचस्प
    0.05
     самому
    0.05
     tenacious
    0.05
     astonishing
    0.05
    Loy
    0.05
    様々な
    0.05
    Activations Density 0.000%

    No Known Activations