© 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. 119389
    Prev
    Next
    INDEX
    Explanations

    section headings or introductions

    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
     completo
    -0.06
    specifically
    -0.06
     তাঁর
    -0.06
     Graffiti
    -0.06
     malattia
    -0.06
     campaigns
    -0.06
     Републи
    -0.06
     উপল
    -0.06
    ပေါ်
    -0.06
     পাখির
    -0.05
    POSITIVE LOGITS
     exceedingly
    0.08
     rare
    0.08
     unusually
    0.07
     কমাতে
    0.06
     cherished
    0.06
     ‎
    0.06
     very
    0.06
     unusual
    0.06
     außergewöhn
    0.06
     case
    0.06
    Activations Density 0.002%

    No Known Activations