© 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. 120779
    Prev
    Next
    INDEX
    Explanations

    Q: followed by question text

    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
    Not in Any Lists

    No Comments

    Negative Logits
     (%
    -0.06
     amazement
    -0.06
     fantasies
    -0.06
     Titanic
    -0.06
    এর
    -0.06
    τια
    -0.06
    Percentages
    -0.06
     वास्तविकता
    -0.06
    artificial
    -0.06
     finite
    -0.06
    POSITIVE LOGITS
     ഒറ്റ
    0.07
    bucks
    0.06
     hyperlinks
    0.06
     protects
    0.06
     связи
    0.06
     plass
    0.06
     하는데
    0.05
    ється
    0.05
     vind
    0.05
    Protect
    0.05
    Activations Density 0.002%

    No Known Activations