© 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. 116477
    Prev
    Next
    INDEX
    Explanations

    numbers and mathematical context

    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
     stedet
    -0.06
    ﹁
    -0.06
     لپاره
    -0.06
     að
    -0.06
    atrième
    -0.06
     at
    -0.05
    issime
    -0.05
    …,
    -0.05
    라도
    -0.05
     schließlich
    -0.05
    POSITIVE LOGITS
     solely
    0.06
    larini
    0.06
    드시
    0.06
    」。
    0.06
    ध्यक्ष
    0.06
    ؟.
    0.06
    只
    0.06
     rant
    0.06
     предусматри
    0.06
     cio
    0.06
    Activations Density 0.001%

    No Known Activations