© 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. 131011
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
     occasionally
    -0.07
    ঊ
    -0.06
     எப்போதும்
    -0.06
     kleine
    -0.06
     potentially
    -0.06
    यद
    -0.06
    ząc
    -0.06
     নীল
    -0.06
     usually
    -0.06
     చిన్న
    -0.06
    POSITIVE LOGITS
     nhưng
    0.07
     Umfang
    0.07
     but
    0.06
     как
    0.06
     relacionada
    0.06
    кто
    0.06
    വ്ര
    0.06
     như
    0.06
     내용
    0.06
     debes
    0.06
    Activations Density 0.003%

    No Known Activations