© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130720
    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
     strong
    -0.06
     главной
    -0.06
    qus
    -0.06
    ⊙
    -0.06
     কেবলমাত্র
    -0.05
     also
    -0.05
    にも
    -0.05
     {{
    -0.05
     Also
    -0.05
     any
    -0.05
    POSITIVE LOGITS
     Wired
    0.07
    Modifier
    0.07
     ขณะ
    0.06
    年間
    0.06
    Puede
    0.06
     wówczas
    0.06
     protože
    0.06
     laissant
    0.06
     बनाकर
    0.06
     لع
    0.06
    Activations Density 0.000%

    No Known Activations