© 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. 129560
    Prev
    Next
    INDEX
    Explanations

    United States, residents, emigrate

    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
    -0.07
     Opposite
    -0.06
    खर
    -0.06
     legale
    -0.06
     மாநக
    -0.06
     законом
    -0.06
     lawful
    -0.06
     partout
    -0.05
     από
    -0.05
     lawfully
    -0.05
    POSITIVE LOGITS
     diminished
    0.06
    通常の
    0.06
     Zusammen
    0.06
    沉默
    0.06
    libro
    0.06
     libro
    0.06
     unusually
    0.06
     कोणताही
    0.06
    立方
    0.06
     td
    0.06
    Activations Density 0.023%

    No Known Activations