© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 121015
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and 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
    Negative Logits
     accidentally
    -0.06
    !).
    -0.06
    %).
    -0.06
    }\}$.
    -0.06
    rman
    -0.06
     :).
    -0.06
    island
    -0.05
     makes
    -0.05
    ร่าง
    -0.05
     ചെറിയ
    -0.05
    POSITIVE LOGITS
     beserta
    0.06
    Mits
    0.06
    乃至
    0.06
    以及
    0.06
    或是
    0.06
     povol
    0.06
     décrite
    0.06
     fluorine
    0.06
     patip
    0.06
    ClassName
    0.06
    Activations Density 0.002%

    No Known Activations