© 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. 120451
    Prev
    Next
    INDEX
    Explanations

    toggle switch

    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
    assertSame
    -0.08
    Indexing
    -0.07
     円
    -0.07
    音樂
    -0.06
     функції
    -0.06
    getName
    -0.06
    ₅
    -0.06
     collegamento
    -0.06
     коктей
    -0.06
    बै
    -0.06
    POSITIVE LOGITS
     o
    0.06
    /
    0.06
    न्न
    0.06
    ोत्तर
    0.06
    一方
    0.06
     criar
    0.06
    。
    0.06
    aa
    0.05
     Biology
    0.05
     overw
    0.05
    Activations Density 0.002%

    No Known Activations