© 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. 117899
    Prev
    Next
    INDEX
    Explanations

    baptized Sikhs

    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
     it
    -0.07
     по
    -0.06
     više
    -0.06
     erroneous
    -0.06
    शिता
    -0.06
     на
    -0.06
    မှ
    -0.06
    वरणीय
    -0.06
     ایک
    -0.06
     अदा
    -0.06
    POSITIVE LOGITS
     importantly
    0.06
     собственно
    0.06
     crucially
    0.06
     ধীরে
    0.06
     mobility
    0.06
     хра
    0.06
     quintessential
    0.06
    滟
    0.06
    SearchParams
    0.06
     राष्ट्रीय
    0.06
    Activations Density 0.008%

    No Known Activations