© 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. 116104
    Prev
    Next
    INDEX
    Explanations

    small / diminutive

    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
     Highest
    -0.06
    राष्ट
    -0.06
     modulates
    -0.06
     ম্যাগ
    -0.06
    的世界
    -0.06
    করা
    -0.06
     worship
    -0.06
     terv
    -0.06
    人用
    -0.06
    allelujah
    -0.06
    POSITIVE LOGITS
     صغير
    0.07
     small
    0.06
     diminu
    0.06
     небольшой
    0.06
     pregnancy
    0.06
    🥟
    0.06
     неболь
    0.06
     kleine
    0.06
    小
    0.06
     کوچ
    0.06
    Activations Density 0.008%

    No Known Activations