© 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. 119589
    Prev
    Next
    INDEX
    Explanations

    proportionate allocation or computation

    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
     입니다
    -0.07
     crítico
    -0.06
     додат
    -0.06
     എന്നതാണ്
    -0.06
     önemli
    -0.06
     additional
    -0.06
     Именно
    -0.06
    が増
    -0.06
     zusätzlichen
    -0.06
     који
    -0.06
    POSITIVE LOGITS
     trzy
    0.06
     مع
    0.06
     proportionate
    0.06
     SOLUTIONS
    0.06
    portion
    0.06
    に基づいて
    0.06
    وزيع
    0.06
     multimedia
    0.06
     उपासना
    0.06
     priori
    0.06
    Activations Density 0.002%

    No Known Activations