© 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. 128330
    Prev
    Next
    INDEX
    Explanations

    development team

    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
     inventions
    -0.06
     centralized
    -0.06
     portable
    -0.06
     methods
    -0.06
     decentralized
    -0.06
    Ề
    -0.05
     chaired
    -0.05
     criteria
    -0.05
     വിദ്യാ
    -0.05
    U
    -0.05
    POSITIVE LOGITS
     nhưng
    0.07
     piensan
    0.07
     filming
    0.06
    较高的
    0.06
     videa
    0.06
    と思っていた
    0.06
     Jur
    0.06
    䧼
    0.06
    ोटेन
    0.06
     fuertes
    0.06
    Activations Density 0.005%

    No Known Activations