© 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. 129976
    Prev
    Next
    INDEX
    Explanations

    code variable declarations

    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
    autocon
    -0.07
     iar
    -0.07
     pertanto
    -0.06
     cần
    -0.06
     вашу
    -0.06
     permitirá
    -0.06
     nécessaire
    -0.06
     permita
    -0.06
     Dl
    -0.06
     alors
    -0.06
    POSITIVE LOGITS
     მისი
    0.07
     violência
    0.07
     그의
    0.06
     proti
    0.06
    旗下
    0.06
     its
    0.06
     منه
    0.06
    ঘুম
    0.06
    its
    0.06
    }$-
    0.06
    Activations Density 0.005%

    No Known Activations