© 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. 120721
    Prev
    Next
    INDEX
    Explanations

    buy speedo swimwear

    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
     कुटुंबा
    -0.05
     genitori
    -0.05
     জ্ঞান
    -0.05
    I
    -0.05
    пси
    -0.05
     λοι
    -0.05
     rodzin
    -0.05
     handcuffed
    -0.05
     ব্যক্তির
    -0.05
     njih
    -0.05
    POSITIVE LOGITS
    ługa
    0.07
     leaped
    0.07
     દર્
    0.06
    exploitation
    0.06
     Rolle
    0.06
    打算
    0.06
     Leop
    0.06
     такими
    0.06
     желания
    0.06
     Fredrik
    0.06
    Activations Density 0.002%

    No Known Activations