© 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. 128735
    Prev
    Next
    INDEX
    Explanations

    code definition keywords

    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
     lanza
    -0.07
     ৪৯
    -0.07
     launch
    -0.07
    聽到
    -0.07
     zahlreichen
    -0.06
    Launch
    -0.06
     konkrét
    -0.06
     dalších
    -0.06
     zahlreiche
    -0.06
     celebrity
    -0.06
    POSITIVE LOGITS
    ,
    0.06
    "></
    0.05
     그리고
    0.05
    מוש
    0.05
     وحتى
    0.05
    ki
    0.05
     поддержку
    0.05
     victime
    0.05
     moest
    0.05
    alty
    0.05
    Activations Density 0.001%

    No Known Activations