© 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. 120678
    Prev
    Next
    INDEX
    Explanations

    import * from

    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
    ,
    -0.06
     involved
    -0.06
     characteristic
    -0.06
    argu
    -0.06
     supplier
    -0.06
     retirement
    -0.06
     involvement
    -0.06
    俗
    -0.06
     typical
    -0.06
    ################
    -0.06
    POSITIVE LOGITS
     प्रक्रियाओं
    0.07
     procesos
    0.07
     processos
    0.07
     processes
    0.06
     processi
    0.06
     আপনার
    0.06
    ıntı
    0.06
     Prozesse
    0.06
     Processes
    0.06
     tři
    0.06
    Activations Density 0.006%

    No Known Activations