© 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. 115888
    Prev
    Next
    INDEX
    Explanations

    game series had now expanded

    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
    ónicos
    -0.06
     besonders
    -0.06
     మీద
    -0.06
     especially
    -0.06
    较大
    -0.06
    Ent
    -0.06
     تطوير
    -0.06
    誉
    -0.06
     অনেকটা
    -0.06
    Faster
    -0.06
    POSITIVE LOGITS
     제가
    0.06
    FINE
    0.06
     jaj
    0.06
    ได้
    0.06
    olog
    0.06
     क्योंकि
    0.06
     Attempt
    0.06
     फैक्ट
    0.06
    swf
    0.05
    餚
    0.05
    Activations Density 0.007%

    No Known Activations