© 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. 130258
    Prev
    Next
    INDEX
    Explanations

    beginnings of lists, questions, or titles

    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
     或者
    -0.06
     purpos
    -0.06
    lify
    -0.06
    inded
    -0.06
    প্
    -0.06
    もしくは
    -0.06
     livelihoods
    -0.05
     방법에
    -0.05
    Muk
    -0.05
    reen
    -0.05
    POSITIVE LOGITS
     большой
    0.07
     нужно
    0.07
     major
    0.07
     güzel
    0.06
     mostrar
    0.06
     需要
    0.06
    อากาศ
    0.06
     árabe
    0.06
     필요한
    0.06
    गात
    0.06
    Activations Density 0.008%

    No Known Activations