© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 127935
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by article

    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
    Negative Logits
     overcame
    -0.06
     تقدر
    -0.06
     gives
    -0.06
     geldi
    -0.06
    同时
    -0.05
     excellently
    -0.05
    geries
    -0.05
    ^{*}$
    -0.05
     сделали
    -0.05
    ந்த்
    -0.05
    POSITIVE LOGITS
     sepanjang
    0.06
     simples
    0.06
    当你
    0.06
    Addressing
    0.06
     Lorsque
    0.06
     deren
    0.06
     apabila
    0.06
     semplici
    0.06
     anyway
    0.06
    alah
    0.06
    Activations Density 0.005%

    No Known Activations