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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130790
    Prev
    Next
    INDEX
    Explanations

    path = "\"

    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
     ममता
    -0.07
    endip
    -0.06
     merely
    -0.06
    ваться
    -0.06
     simple
    -0.06
     local
    -0.06
     diligent
    -0.05
     critical
    -0.05
     careful
    -0.05
     প্রত্যাবর্তন
    -0.05
    POSITIVE LOGITS
     لكن
    0.07
     until
    0.07
    わざ
    0.06
     vieron
    0.06
     jusqu
    0.06
     but
    0.06
    杍
    0.06
     piled
    0.06
    🎸
    0.06
    정에
    0.06
    Activations Density 0.001%

    No Known Activations