© 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. 130130
    Prev
    Next
    INDEX
    Explanations

    code 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
     Delaware
    -0.06
    Known
    -0.06
     juntos
    -0.06
     rhyme
    -0.06
    들은
    -0.06
     thanks
    -0.06
    Probably
    -0.06
    â
    -0.06
    就是在
    -0.06
    known
    -0.06
    POSITIVE LOGITS
     not
    0.07
    тря
    0.06
     truly
    0.06
     naprawdę
    0.06
     realmente
    0.06
     genuinely
    0.06
    的一切
    0.06
     paraf
    0.06
    çı
    0.06
     যায়নি
    0.06
    Activations Density 0.001%

    No Known Activations