© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129784
    Prev
    Next
    INDEX
    Explanations

    unlock, discover, buy, drop

    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
     szá
    -0.06
     gdje
    -0.06
    含义
    -0.06
                        
    -0.06
     пе
    -0.06
    ları
    -0.06
    弱
    -0.06
    opedic
    -0.06
                          
    -0.06
    τικά
    -0.06
    POSITIVE LOGITS
    ครบ
    0.07
    Restrictions
    0.06
    discover
    0.06
    発見
    0.06
     발견
    0.06
    access
    0.06
    Discover
    0.06
     буде
    0.06
     появление
    0.06
     नहीं
    0.06
    Activations Density 0.004%

    No Known Activations