© 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. 131069
    Prev
    Next
    INDEX
    Explanations

    function definitions and arguments

    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
     Aktiv
    -0.06
     哦
    -0.06
    உங்கள்
    -0.06
     concaten
    -0.06
     الجميع
    -0.06
     which
    -0.06
     maximizing
    -0.06
     architectures
    -0.06
     coord
    -0.06
     affili
    -0.06
    POSITIVE LOGITS
     sometimes
    0.07
    sometimes
    0.06
     tanpa
    0.06
     ما
    0.06
     often
    0.06
    9
    0.06
     প্রায়
    0.06
    .
    0.06
    经常
    0.05
     estava
    0.05
    Activations Density 0.004%

    No Known Activations