© 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. 121029
    Prev
    Next
    INDEX
    Explanations

    UIImage, Bitmap, BufferedImage

    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
    គ្រ
    -0.08
     наверное
    -0.07
     única
    -0.07
     pursue
    -0.07
     преимущества
    -0.06
    باح
    -0.06
     únic
    -0.06
     simplemente
    -0.06
     unik
    -0.06
     wú
    -0.06
    POSITIVE LOGITS
     ইহার
    0.06
    哪
    0.06
    Irr
    0.06
    bff
    0.06
    Applying
    0.05
     settings
    0.05
     bagaimana
    0.05
     davranış
    0.05
    िस्थित
    0.05
    仄
    0.05
    Activations Density 0.004%

    No Known Activations