© 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. 129729
    Prev
    Next
    INDEX
    Explanations

    start of a sentence or phrase

    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
    变化的
    -0.06
     changes
    -0.06
    alia
    -0.06
     neues
    -0.06
     Toilet
    -0.06
     Times
    -0.06
     इतर
    -0.06
    出来的
    -0.06
     Brexit
    -0.06
     new
    -0.06
    POSITIVE LOGITS
     Inicial
    0.07
    专业的
    0.06
    Inicial
    0.06
     indoctr
    0.06
     Install
    0.06
    initial
    0.06
    initialize
    0.06
     initialize
    0.06
     instalar
    0.06
    ార్
    0.06
    Activations Density 0.003%

    No Known Activations