© 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. 127909
    Prev
    Next
    INDEX
    Explanations

    closing punctuation and code blocks

    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
     на
    -0.07
     things
    -0.06
     в
    -0.06
     препарат
    -0.06
     Things
    -0.06
    选中
    -0.06
     Cane
    -0.06
     製品
    -0.06
     atleta
    -0.06
     हमारी
    -0.06
    POSITIVE LOGITS
    除了
    0.06
    ∩
    0.06
     これは
    0.06
    many
    0.06
    还有
    0.06
     Corollary
    0.06
     muitas
    0.06
     również
    0.06
     虽然
    0.06
     Многие
    0.06
    Activations Density 0.002%

    No Known Activations