© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119458
    Prev
    Next
    INDEX
    Explanations

    Android devices and operating systems

    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
     comfortable
    -0.06
     twee
    -0.06
    ണ്ട്
    -0.06
     পরিস্কার
    -0.06
     healthy
    -0.06
     HSPB
    -0.06
     வெள்ளை
    -0.06
     mandatory
    -0.06
     Farr
    -0.06
     subparagraph
    -0.06
    POSITIVE LOGITS
     Constants
    0.06
     Reference
    0.06
    please
    0.06
    実際の
    0.06
    described
    0.06
     букме
    0.06
     constants
    0.06
    to
    0.06
    Reference
    0.06
    参考
    0.06
    Activations Density 0.012%

    No Known Activations