© 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. 118251
    Prev
    Next
    INDEX
    Explanations

    state regulatory and classifieds

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     legally
    -0.08
    アプリ
    -0.06
     trademark
    -0.06
     পার্থক্য
    -0.06
     юриди
    -0.06
     noteworthy
    -0.06
     permitted
    -0.06
     famous
    -0.06
    Highlight
    -0.06
    incl
    -0.06
    POSITIVE LOGITS
     housewife
    0.06
     zad
    0.06
     अद
    0.06
     불안
    0.06
     riego
    0.06
     nicht
    0.06
     chacune
    0.06
     Hier
    0.05
    प्रमाणे
    0.05
     extract
    0.05
    Activations Density 0.010%

    No Known Activations