© 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. 121066
    Prev
    Next
    INDEX
    Explanations

    Interstate highways

    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
     when
    -0.06
    att
    -0.06
    Already
    -0.06
     verdict
    -0.06
     headcount
    -0.05
    例如
    -0.05
     Already
    -0.05
    persistent
    -0.05
     Forge
    -0.05
     already
    -0.05
    POSITIVE LOGITS
     blooming
    0.06
     hasta
    0.06
     исключительно
    0.06
     அவரை
    0.06
     அடிப்படையில்
    0.06
    熊猫
    0.06
     unpublished
    0.06
     cinqu
    0.06
     झांसी
    0.06
     интересный
    0.06
    Activations Density 0.009%

    No Known Activations