© 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. 119079
    Prev
    Next
    INDEX
    Explanations

    overflow: hidden

    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
    他还
    -0.06
     Ransom
    -0.06
    未必
    -0.06
     있고요
    -0.06
     staying
    -0.06
    வையாக
    -0.05
     nevoia
    -0.05
     Traditional
    -0.05
     lengths
    -0.05
     leisurely
    -0.05
    POSITIVE LOGITS
    將
    0.07
     의해
    0.07
     trên
    0.06
    商品的
    0.06
     WHEN
    0.06
     selecting
    0.06
     بر
    0.06
     során
    0.06
    产品的
    0.06
     wyra
    0.06
    Activations Density 0.001%

    No Known Activations