© 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. 130351
    Prev
    Next
    INDEX
    Explanations

    math include files

    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
     hàn
    -0.06
     determining
    -0.06
     determ
    -0.06
     disminuir
    -0.06
     亻
    -0.06
     così
    -0.06
     Hãy
    -0.06
     ಶತ
    -0.06
     Determine
    -0.06
     मतलब
    -0.06
    POSITIVE LOGITS
     with
    0.08
     WITH
    0.07
     unmatched
    0.06
     tools
    0.06
     has
    0.06
     With
    0.06
     preocupa
    0.06
     its
    0.06
     to
    0.06
     by
    0.06
    Activations Density 0.003%

    No Known Activations