© 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. 117569
    Prev
    Next
    INDEX
    Explanations

    numbers, and common words after 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
    现在
    -0.06
     humorous
    -0.06
     miesięcy
    -0.06
     your
    -0.06
    credibly
    -0.06
     사람
    -0.06
    ရှင်း
    -0.06
    currentCharacter
    -0.06
     서
    -0.06
    Specular
    -0.06
    POSITIVE LOGITS
    まずは
    0.07
     optimal
    0.06
     by
    0.05
     оптима
    0.05
     تحریک
    0.05
     whereas
    0.05
     বছরে
    0.05
    訛
    0.05
     ಕ್ಷೇತ್ರದ
    0.05
    最佳
    0.05
    Activations Density 0.009%

    No Known Activations