© 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. 117055
    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
    Not in Any Lists

    No Comments

    Negative Logits
     imitation
    -0.07
     दूस
    -0.07
     four
    -0.06
     самостоя
    -0.06
    代わりに
    -0.05
    它
    -0.05
    four
    -0.05
     üç
    -0.05
     investigar
    -0.05
     четырех
    -0.05
    POSITIVE LOGITS
     платье
    0.06
     those
    0.06
     punitive
    0.06
    尽可能
    0.06
     অভিযোগে
    0.06
    👑
    0.06
    笥
    0.06
    those
    0.06
     दिवस
    0.06
     때문에
    0.06
    Activations Density 0.002%

    No Known Activations