© 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. 128112
    Prev
    Next
    INDEX
    Explanations

    Fort Bragg

    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
    -0.07
     която
    -0.06
     เมื่อ
    -0.06
    when
    -0.06
     Daniel
    -0.06
     জেট
    -0.06
    which
    -0.05
    카드
    -0.05
     техни
    -0.05
    ikaner
    -0.05
    POSITIVE LOGITS
    :
    0.07
     le
    0.06
     vacant
    0.06
     her
    0.06
     다양한
    0.06
    َت
    0.06
     Piv
    0.06
     dei
    0.06
     potential
    0.06
     widespread
    0.06
    Activations Density 0.001%

    No Known Activations