© 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. 120739
    Prev
    Next
    INDEX
    Explanations

    difficult or hard to

    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
    很容易
    -0.07
     बना
    -0.06
     each
    -0.06
     ezért
    -0.06
     dễ
    -0.06
     δύ
    -0.06
     ಮತ್ತೆ
    -0.06
     chacune
    -0.06
     willingness
    -0.06
    各
    -0.06
    POSITIVE LOGITS
     सरकारच्या
    0.07
     being
    0.07
     improve
    0.07
     же
    0.06
     назвать
    0.06
    ᴀ
    0.06
     zostać
    0.06
     efficient
    0.06
     त्याच
    0.06
    われて
    0.06
    Activations Density 0.006%

    No Known Activations