© 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. 120755
    Prev
    Next
    INDEX
    Explanations

    selection choice

    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
     puisi
    -0.07
     novelists
    -0.06
    ื่อง
    -0.06
    ructures
    -0.06
     شاعر
    -0.06
    ジュール
    -0.06
     recreated
    -0.06
     carved
    -0.06
     carvings
    -0.06
    cję
    -0.06
    POSITIVE LOGITS
     انتخاب
    0.09
     เลือก
    0.08
     vyber
    0.07
     selezion
    0.07
     analysis
    0.07
     wrong
    0.07
     výbě
    0.06
     fondament
    0.06
     выборе
    0.06
    เลือก
    0.06
    Activations Density 0.001%

    No Known Activations