© 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. 116032
    Prev
    Next
    INDEX
    Explanations

    introductionassociateddecodingforum

    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
    marketing
    -0.07
    經過
    -0.06
    市長
    -0.06
     different
    -0.06
     goals
    -0.06
     economic
    -0.06
     dvd
    -0.06
     আমাদেরকে
    -0.06
    gluten
    -0.06
     dissimilar
    -0.06
    POSITIVE LOGITS
     diğer
    0.06
     зимой
    0.06
     autres
    0.06
     інших
    0.06
    在日本
    0.06
     otros
    0.06
     dalších
    0.06
     otras
    0.06
     দক্ষিণে
    0.06
     outras
    0.06
    Activations Density 0.001%

    No Known Activations