© 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. 129818
    Prev
    Next
    INDEX
    Explanations

    growing up, timeline

    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
    yielding
    -0.06
    一代
    -0.06
     env
    -0.06
     broad
    -0.06
     envy
    -0.06
     extensible
    -0.06
    љ
    -0.06
     good
    -0.05
     அட்சய
    -0.05
    instruct
    -0.05
    POSITIVE LOGITS
    招聘
    0.06
     indígen
    0.06
     RI
    0.06
    🐆
    0.06
     आमतौर
    0.06
    如果你
    0.06
     LGBT
    0.06
    🈷
    0.06
    并且
    0.06
    ணன்
    0.06
    Activations Density 0.004%

    No Known Activations