© 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. 119083
    Prev
    Next
    INDEX
    Explanations

    page, article, news, info

    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
     Itali
    -0.06
    而不是
    -0.06
     önces
    -0.06
    rador
    -0.05
     αλλά
    -0.05
    将在
    -0.05
    yil
    -0.05
     पैकेज
    -0.05
    交叉
    -0.05
     Trial
    -0.05
    POSITIVE LOGITS
    Compatible
    0.07
     specify
    0.07
     compatible
    0.07
     specifies
    0.07
    Diverse
    0.06
     видим
    0.06
     postup
    0.06
    ㄣ
    0.06
     Gradually
    0.06
     metade
    0.06
    Activations Density 0.001%

    No Known Activations