© 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. 129484
    Prev
    Next
    INDEX
    Explanations

    U.S. Pat., Structo®, Q:, Homotopic, 1

    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
     livestock
    -0.07
    經常
    -0.07
    Agricultural
    -0.07
     agricultural
    -0.07
     круп
    -0.07
    经常
    -0.07
     산업
    -0.06
    Industrial
    -0.06
     intimidating
    -0.06
     biomass
    -0.06
    POSITIVE LOGITS
     health
    0.07
     acolo
    0.07
     clinical
    0.07
     whirlpool
    0.07
    へと
    0.07
     Clinical
    0.06
     agent
    0.06
     physicians
    0.06
     doctor
    0.06
     Health
    0.06
    Activations Density 0.005%

    No Known Activations