© 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. 116310
    Prev
    Next
    INDEX
    Explanations

    child or girl

    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
    뗀
    -0.06
     Tempor
    -0.06
     তাঁদের
    -0.06
    खाना
    -0.06
    Tres
    -0.05
     প্রথমবারের
    -0.05
    groupId
    -0.05
    लाइ
    -0.05
     circumfer
    -0.05
    开始
    -0.05
    POSITIVE LOGITS
     selective
    0.08
     선택
    0.07
     Selective
    0.07
     પસંદ
    0.07
     ここ
    0.07
    编程
    0.06
    可以选择
    0.06
    选择了
    0.06
     scelta
    0.06
    選択
    0.06
    Activations Density 0.006%

    No Known Activations