© 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. 120679
    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
     dense
    -0.06
     very
    -0.05
    Academic
    -0.05
    dense
    -0.05
     itself
    -0.05
    の中心
    -0.05
     Hasht
    -0.05
    blas
    -0.05
     的
    -0.05
    security
    -0.05
    POSITIVE LOGITS
     različ
    0.08
     różne
    0.08
     forskjellige
    0.07
     örnek
    0.07
     potrzeb
    0.07
     hitta
    0.07
     verschiedene
    0.07
     다양한
    0.07
     వివిధ
    0.07
    해야
    0.07
    Activations Density 0.000%

    No Known Activations