© 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. 118896
    Prev
    Next
    INDEX
    Explanations

    names ending in ston, ley, son, ler

    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
    approximately
    -0.06
    뺄
    -0.06
    整个
    -0.06
    》（
    -0.06
     reduction
    -0.06
     आये
    -0.06
     hjel
    -0.06
     ಸಂತ
    -0.06
    )-
    -0.06
     institutional
    -0.06
    POSITIVE LOGITS
    1
    0.06
     zoveel
    0.06
     О
    0.06
     метода
    0.06
    डान
    0.06
    Having
    0.06
     А
    0.06
     kurzen
    0.06
     …….
    0.06
     But
    0.06
    Activations Density 0.048%

    No Known Activations