© 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. 119038
    Prev
    Next
    INDEX
    Explanations

    numbers and variables in equations

    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
     and
    -0.07
     হউক
    -0.06
    mathcal
    -0.06
    emoration
    -0.06
     fazendo
    -0.06
    Adding
    -0.06
     adding
    -0.06
    Maybe
    -0.06
     Adding
    -0.05
    完成
    -0.05
    POSITIVE LOGITS
    ,»
    0.07
     её
    0.07
     của
    0.07
     ее
    0.07
     versatile
    0.07
    subseteq
    0.06
    都是
    0.06
     by
    0.06
     стиля
    0.06
     ফেসব
    0.06
    Activations Density 0.001%

    No Known Activations