© 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. 117558
    Prev
    Next
    INDEX
    Explanations

    non-English words and symbols

    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
     aftermath
    -0.07
     amendments
    -0.06
    详细
    -0.06
    建议
    -0.06
    🩹
    -0.06
    についての
    -0.06
     duration
    -0.06
     documentation
    -0.06
     february
    -0.06
     JFrame
    -0.06
    POSITIVE LOGITS
     იყოს
    0.06
     ALL
    0.06
     essere
    0.06
     إلا
    0.06
     rediscovered
    0.06
    apparition
    0.06
     unfiltered
    0.06
    แบ่ง
    0.06
    All
    0.06
     Sperm
    0.06
    Activations Density 0.002%

    No Known Activations