© 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. 117837
    Prev
    Next
    INDEX
    Explanations

    the: author, title, case

    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
    脚步
    -0.07
     dvije
    -0.06
     dvě
    -0.06
     two
    -0.06
     analogue
    -0.06
     două
    -0.06
     ಎರಡು
    -0.06
     две
    -0.06
     
    -0.06
    ❶
    -0.06
    POSITIVE LOGITS
     खुशखबरी
    0.06
     impacts
    0.06
     இதன்
    0.06
     đạt
    0.06
    🥶
    0.06
    urization
    0.06
     इनकम
    0.05
    Because
    0.05
     খাওয়ার
    0.05
     ነገ
    0.05
    Activations Density 0.006%

    No Known Activations