© 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. 117216
    Prev
    Next
    INDEX
    Explanations

    numbers with units

    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
    采集
    -0.07
     Conditioner
    -0.06
    সঙ্গে
    -0.06
     коллек
    -0.06
     verschiedenen
    -0.06
     கொண்டிருக்கும்
    -0.06
    皆さん
    -0.06
    同学们
    -0.06
     колек
    -0.06
    Bor
    -0.06
    POSITIVE LOGITS
    NotFound
    0.08
     dès
    0.06
     disruptions
    0.06
     Minaj
    0.06
     आधे
    0.06
     উন্নয়নে
    0.06
    ブリッド
    0.06
    still
    0.06
    ɛ
    0.06
     distinguish
    0.06
    Activations Density 0.003%

    No Known Activations