© 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. 116442
    Prev
    Next
    INDEX
    Explanations

    specific objects and concepts

    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
    ;
    -0.09
    ；
    -0.06
     the
    -0.06
     precursors
    -0.06
    hellip
    -0.06
    ক্ষা
    -0.06
     постоян
    -0.06
     continually
    -0.06
    ന്ദ്ര
    -0.06
     Noor
    -0.06
    POSITIVE LOGITS
     Enjoy
    0.06
    赶紧
    0.06
    LGBT
    0.06
     MAKE
    0.06
     પ્રવેશ
    0.06
     funniest
    0.06
    渴望
    0.06
    MAKE
    0.05
     booze
    0.05
     percib
    0.05
    Activations Density 0.003%

    No Known Activations