© 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. 128981
    Prev
    Next
    INDEX
    Explanations

    invention and technical specifications

    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
    記得
    -0.07
     Office
    -0.06
    office
    -0.06
     Use
    -0.06
     используется
    -0.06
     केमिकल
    -0.06
    Office
    -0.06
    īj
    -0.06
     используются
    -0.06
     ઉપયોગ
    -0.06
    POSITIVE LOGITS
     정보를
    0.07
     restaur
    0.06
     Celebr
    0.06
     disabled
    0.06
     supporters
    0.06
     предусмотре
    0.06
     humidifier
    0.06
     retailer
    0.06
    完善
    0.06
     private
    0.06
    Activations Density 0.006%

    No Known Activations