© 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. 120997
    Prev
    Next
    INDEX
    Explanations

    instructions and guidelines

    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
     resultados
    -0.07
     máme
    -0.06
     СССР
    -0.06
     واضح
    -0.06
    famous
    -0.06
     общей
    -0.06
     sauver
    -0.06
     रिपोर्ट्स
    -0.06
     показывает
    -0.06
     sonuç
    -0.06
    POSITIVE LOGITS
    を知
    0.07
     instructions
    0.07
     will
    0.06
     might
    0.06
    จะ
    0.06
     Guide
    0.06
    Instruction
    0.06
     announce
    0.05
    /*
    0.05
     instruction
    0.05
    Activations Density 0.011%

    No Known Activations