© 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. 120889
    Prev
    Next
    INDEX
    Explanations

    missing or blank values

    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
     something
    -0.07
     like
    -0.07
     ಹೆಸ
    -0.06
     partículas
    -0.06
     ছোট্ট
    -0.06
     просто
    -0.06
    linewidth
    -0.05
    detalle
    -0.05
    နှင့်
    -0.05
    Something
    -0.05
    POSITIVE LOGITS
    dns
    0.06
     plupart
    0.06
    จ
    0.06
    داث
    0.06
     calculations
    0.06
    挨拶
    0.06
     তিনি
    0.06
    他还
    0.05
     Consistency
    0.05
     dateFormat
    0.05
    Activations Density 0.008%

    No Known Activations