© 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. 128074
    Prev
    Next
    INDEX
    Explanations

    live music venues

    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
     transformative
    -0.07
    ippings
    -0.06
     Produto
    -0.06
     transforma
    -0.06
     Teal
    -0.06
    creet
    -0.06
     हराकर
    -0.06
    秸
    -0.06
    transform
    -0.06
    reas
    -0.06
    POSITIVE LOGITS
    竞争
    0.06
     inhibition
    0.06
    ision
    0.06
     Air
    0.06
    aggressive
    0.06
    بیه
    0.05
     affected
    0.05
    取决于
    0.05
    库存
    0.05
     biasanya
    0.05
    Activations Density 0.068%

    No Known Activations