© 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. 120533
    Prev
    Next
    INDEX
    Explanations

    abbreviations followed by punctuation

    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
    其他人
    -0.06
     troubles
    -0.06
     পরিবর্তে
    -0.06
     অন্যরা
    -0.06
     Troubles
    -0.06
     mauve
    -0.06
    ٦
    -0.06
     разработки
    -0.06
     froide
    -0.06
     others
    -0.06
    POSITIVE LOGITS
    脚注
    0.06
     tempt
    0.06
    થી
    0.06
     ЕС
    0.05
     धमाकेदार
    0.05
     primordial
    0.05
     sav
    0.05
     주목
    0.05
    ada
    0.05
     უნდა
    0.05
    Activations Density 0.044%

    No Known Activations