© 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. 128036
    Prev
    Next
    INDEX
    Explanations

    numbers followed by code or 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
    Negative Logits
     سایر
    -0.07
     diğer
    -0.07
     other
    -0.07
     Nullam
    -0.07
     अन्य
    -0.07
    ]=="
    -0.06
     tính
    -0.06
     omoguć
    -0.06
    Eventually
    -0.06
    ORE
    -0.06
    POSITIVE LOGITS
    .
    0.07
    ทำงาน
    0.06
     такую
    0.06
    ιχ
    0.05
     such
    0.05
     kami
    0.05
     mustn
    0.05
    ampa
    0.05
     त्यांना
    0.05
     Deeds
    0.05
    Activations Density 0.001%

    No Known Activations