© 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. 117756
    Prev
    Next
    INDEX
    Explanations

    forms of "to be" or "needed"

    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
    pung
    -0.07
     یافت
    -0.06
     그리고
    -0.06
     további
    -0.05
     Background
    -0.05
    émy
    -0.05
     example
    -0.05
     高
    -0.05
     Looks
    -0.05
    example
    -0.05
    POSITIVE LOGITS
    णार
    0.07
    ılı
    0.07
     teilweise
    0.06
     pretensions
    0.06
     ආහාර
    0.06
     epitome
    0.06
    சில
    0.06
     incluida
    0.06
    >/</
    0.06
    时的
    0.06
    Activations Density 0.007%

    No Known Activations