© 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. 119839
    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
     ещё
    -0.07
     According
    -0.07
     หาก
    -0.07
     voor
    -0.07
     için
    -0.07
     für
    -0.07
     jeszcze
    -0.07
    还可以
    -0.07
     Components
    -0.07
     برای
    -0.07
    POSITIVE LOGITS
    never
    0.06
     urg
    0.06
    kaj
    0.05
    both
    0.05
    backup
    0.05
    NOWLED
    0.05
    filt
    0.05
     never
    0.05
     কখনই
    0.05
    BOTH
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.