© 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. 118484
    Prev
    Next
    INDEX
    Explanations

    code comments and javascript

    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
     sont
    -0.07
     neue
    -0.07
    一般的な
    -0.07
     resounding
    -0.07
     weaving
    -0.06
    传统的
    -0.06
     esta
    -0.06
     tienen
    -0.06
     effecting
    -0.06
    ణం
    -0.06
    POSITIVE LOGITS
     не
    0.06
    場面積
    0.06
     সংরক্ষণ
    0.06
    INPUT
    0.06
     अधिक
    0.06
     पूरा
    0.06
    を入れて
    0.06
     Waiting
    0.06
     waiting
    0.06
    okra
    0.06
    Activations Density 0.001%

    No Known Activations