© 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. 119978
    Prev
    Next
    INDEX
    Explanations

    like our, like a, in the, of the

    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
     consecutively
    -0.07
    걍
    -0.07
     একে
    -0.06
    那样
    -0.06
     будут
    -0.06
     उससे
    -0.06
     يعني
    -0.06
     are
    -0.06
    頫
    -0.06
    日起
    -0.06
    POSITIVE LOGITS
    ※
    0.06
     pourtant
    0.06
     embora
    0.06
     bowiem
    0.06
    ሮች
    0.06
     personal
    0.06
     seçim
    0.06
     enveloping
    0.06
     개인
    0.06
     gesamten
    0.06
    Activations Density 0.018%

    No Known Activations