© 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. 129215
    Prev
    Next
    INDEX
    Explanations

    existences and claims

    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
     een
    -0.07
     라는
    -0.07
     initiated
    -0.06
     بندی
    -0.06
    दूसरी
    -0.06
     verschiedenen
    -0.06
     이라고
    -0.06
    شاء
    -0.06
     różne
    -0.06
     ؛
    -0.06
    POSITIVE LOGITS
     WHAT
    0.07
     স্থানে
    0.06
    WHAT
    0.06
     Teacher
    0.06
     numerous
    0.06
    ₨
    0.06
    ★★★
    0.06
     teachers
    0.06
     ครู
    0.06
     সকলকে
    0.06
    Activations Density 0.103%

    No Known Activations