© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118683
    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
     ومش
    -0.06
     kraft
    -0.06
    ensatz
    -0.06
     समेत
    -0.06
     yrs
    -0.06
     entirely
    -0.06
     sessionStorage
    -0.06
     soud
    -0.06
    Memorial
    -0.05
     aident
    -0.05
    POSITIVE LOGITS
     with
    0.07
     general
    0.07
    一般
    0.07
     to
    0.07
     begge
    0.06
    তবে
    0.06
     общей
    0.06
     on
    0.06
     genellikle
    0.06
     beide
    0.06
    Activations Density 0.000%

    No Known Activations