© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130900
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
     continuously
    -0.06
     used
    -0.06
     porque
    -0.06
    ভাগের
    -0.06
     implemented
    -0.06
     repeatedly
    -0.06
     implementing
    -0.06
     основе
    -0.06
     criticized
    -0.05
     করিবার
    -0.05
    POSITIVE LOGITS
     of
    0.07
     you
    0.07
     הן
    0.06
     esempi
    0.06
    जफ्
    0.06
     formulario
    0.06
     সংরক্ষিত
    0.06
     ejemplos
    0.06
     caminos
    0.06
     here
    0.06
    Activations Density 0.005%

    No Known Activations