© 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. 128473
    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
    Who
    -0.07
     Allgemeine
    -0.07
     Align
    -0.06
     Crav
    -0.06
    쉽
    -0.06
     länge
    -0.06
     לפי
    -0.06
    नान
    -0.06
    eneral
    -0.06
    General
    -0.06
    POSITIVE LOGITS
     sometimes
    0.06
     soms
    0.06
     when
    0.06
     likewise
    0.06
     parfois
    0.06
    有时候
    0.05
     Petitioner
    0.05
     नष्ट
    0.05
     do
    0.05
     considerado
    0.05
    Activations Density 0.000%

    No Known Activations