© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119576
    Prev
    Next
    INDEX
    Explanations

    what is the next term?

    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
     like
    -0.07
     ſ
    -0.07
     Like
    -0.06
    fees
    -0.06
    逐渐
    -0.06
     sits
    -0.06
     Houston
    -0.06
     einiger
    -0.06
    เช่น
    -0.06
     स्थान
    -0.06
    POSITIVE LOGITS
    什么
    0.06
     متاثر
    0.06
    への
    0.06
    :
    0.06
     nw
    0.06
    ঈশ্বর
    0.06
     Towa
    0.06
     grandsons
    0.06
    TableRow
    0.06
    
    0.06
    Activations Density 0.001%

    No Known Activations