© 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. 120392
    Prev
    Next
    INDEX
    Explanations

    quotes and punctuation

    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
     絶対
    -0.08
     these
    -0.07
     this
    -0.07
     assolutamente
    -0.07
    ाइड
    -0.07
     用户
    -0.07
     この
    -0.07
     any
    -0.07
     Жи
    -0.07
     ormai
    -0.06
    POSITIVE LOGITS
     રો
    0.05
    wikimedia
    0.05
    POST
    0.05
     minha
    0.05
     aftermath
    0.05
    ُو
    0.05
    ytically
    0.05
     শরত
    0.05
     jälkeen
    0.05
     toppings
    0.05
    Activations Density 0.001%

    No Known Activations