© 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. 129173
    Prev
    Next
    INDEX
    Explanations

    creative writing and outfits

    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
     हमारी
    -0.06
     nebude
    -0.06
     famosa
    -0.06
     RELATED
    -0.06
     ນ
    -0.06
     нещо
    -0.06
    鎊
    -0.06
     უკ
    -0.06
     ئى
    -0.06
     promin
    -0.06
    POSITIVE LOGITS
     thì
    0.07
     ise
    0.07
     sorti
    0.06
    则
    0.06
    上述
    0.06
    ्हान
    0.06
     និង
    0.06
    ých
    0.06
     및
    0.06
    Variety
    0.06
    Activations Density 0.001%

    No Known Activations