© 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. 129700
    Prev
    Next
    INDEX
    Explanations

    type or classification

    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
     products
    -0.07
    Graz
    -0.07
     descarg
    -0.06
     dậy
    -0.06
     savun
    -0.06
    Trendy
    -0.06
     sassy
    -0.06
    生态
    -0.06
    ____
    -0.06
    Markets
    -0.06
    POSITIVE LOGITS
     тип
    0.07
     masterpieces
    0.06
     regresar
    0.06
     Hopefully
    0.06
     superlative
    0.06
     expert
    0.06
     enorm
    0.06
     soch
    0.06
     말씀
    0.06
     tipo
    0.06
    Activations Density 0.003%

    No Known Activations