© 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. 128099
    Prev
    Next
    INDEX
    Explanations

    java package or copyright comments

    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
     INTEREST
    -0.06
     Mister
    -0.05
    ங்களில்
    -0.05
     *
    -0.05
     Den
    -0.05
     cualquiera
    -0.05
     Los
    -0.05
    ❥
    -0.05
     Florida
    -0.05
     ambito
    -0.05
    POSITIVE LOGITS
     chegando
    0.07
     pricing
    0.06
     ჩვენ
    0.06
     learnings
    0.06
    Após
    0.06
    我们
    0.06
     chegada
    0.06
    🦃
    0.06
    我们也
    0.06
     arrived
    0.06
    Activations Density 0.010%

    No Known Activations