© 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. 118018
    Prev
    Next
    INDEX
    Explanations

    declaring html document type

    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
     ALSO
    -0.07
     neuen
    -0.06
     nuovi
    -0.06
     novos
    -0.06
     nuevos
    -0.06
     beiden
    -0.06
     replace
    -0.06
     cherish
    -0.06
    also
    -0.06
     συ
    -0.06
    POSITIVE LOGITS
     Strickland
    0.06
    ختلف
    0.06
     wykorzyst
    0.06
    疣
    0.06
     ile
    0.06
     utiliza
    0.06
     किया
    0.06
    కున్న
    0.06
     میلیارد
    0.06
    トゥーン
    0.06
    Activations Density 0.001%

    No Known Activations