© 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. 115877
    Prev
    Next
    INDEX
    Explanations

    Crimes Act

    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
     ಹಾಗೂ
    -0.07
    тини
    -0.06
    posizione
    -0.06
     இறுதி
    -0.06
     allows
    -0.06
    цый
    -0.06
     valiant
    -0.06
     stylized
    -0.05
     cũng
    -0.05
     stunning
    -0.05
    POSITIVE LOGITS
    ,
    0.06
     svjets
    0.06
    ه‌های
    0.06
    だけで
    0.06
     Global
    0.06
     자체
    0.06
     Dias
    0.06
     Internet
    0.06
     motiv
    0.06
     itself
    0.06
    Activations Density 0.001%

    No Known Activations