© 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. 118697
    Prev
    Next
    INDEX
    Explanations

    integer types and properties

    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
     utilizing
    -0.06
    Созда
    -0.05
     veut
    -0.05
     creates
    -0.05
     akár
    -0.05
     
    -0.05
     عاوز
    -0.05
    どちら
    -0.05
    Create
    -0.05
     সবচে
    -0.05
    POSITIVE LOGITS
     alloying
    0.06
     другие
    0.06
     ответы
    0.06
    他の
    0.06
     Марина
    0.06
     catalysts
    0.06
     оказалась
    0.06
     outras
    0.06
     tranquillity
    0.06
     photographers
    0.06
    Activations Density 0.006%

    No Known Activations