© 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. 120450
    Prev
    Next
    INDEX
    Explanations

    variable names like n, n(, n)

    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
     raisons
    -0.06
     sababu
    -0.06
     fuerte
    -0.06
     blurry
    -0.06
     ಉದ್ದ
    -0.06
     unresolved
    -0.06
     güçlü
    -0.06
     تغییر
    -0.06
     thất
    -0.06
     acuerdo
    -0.06
    POSITIVE LOGITS
     niektórych
    0.07
     некоторых
    0.07
    某些
    0.06
     niektor
    0.06
     podia
    0.06
     primeira
    0.06
     algumas
    0.06
     beberapa
    0.06
     சில
    0.06
    물을
    0.06
    Activations Density 0.030%

    No Known Activations