© 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. 129972
    Prev
    Next
    INDEX
    Explanations

    first number followed by a noun

    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
     each
    -0.07
     overall
    -0.06
     mỗi
    -0.06
     EACH
    -0.06
     continuing
    -0.06
     yearly
    -0.06
     lateribus
    -0.05
     total
    -0.05
    curr
    -0.05
    owi
    -0.05
    POSITIVE LOGITS
     его
    0.08
     comprobar
    0.07
     jego
    0.07
    jego
    0.07
     δεν
    0.07
     секу
    0.06
     שלו
    0.06
     प्रियंका
    0.06
     trochu
    0.06
     Yuki
    0.06
    Activations Density 0.013%

    No Known Activations