© 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. 128720
    Prev
    Next
    INDEX
    Explanations

    radiation exposure

    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
     init
    -0.06
    🚀
    -0.06
    outside
    -0.06
     confronted
    -0.06
     shaped
    -0.06
    line
    -0.06
     fission
    -0.05
     platform
    -0.05
    edition
    -0.05
     expedite
    -0.05
    POSITIVE LOGITS
     erythe
    0.07
     избежать
    0.07
    詬
    0.06
     vermeiden
    0.06
    éviter
    0.06
     éviter
    0.06
     minimizar
    0.06
    传感
    0.06
     sensory
    0.06
     정도
    0.06
    Activations Density 0.013%

    No Known Activations