© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128598
    Prev
    Next
    INDEX
    Explanations

    men and liberals

    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
     converting
    -0.07
     cũng
    -0.06
    誅
    -0.06
     conversion
    -0.06
     গ্রন্থে
    -0.06
     এবং
    -0.06
    šće
    -0.06
     conversions
    -0.06
    ריך
    -0.06
     insertion
    -0.06
    POSITIVE LOGITS
     Analytics
    0.07
     their
    0.07
     kanilang
    0.06
     їх
    0.06
     alot
    0.05
    फोटो
    0.05
     شفاف
    0.05
     afterwards
    0.05
    明
    0.05
    isatie
    0.05
    Activations Density 0.007%

    No Known Activations