© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118434
    Prev
    Next
    INDEX
    Explanations

    humorous view

    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
    Both
    -0.06
     모두
    -0.06
    ทั้งหมด
    -0.06
     entrambi
    -0.06
    Various
    -0.06
    ழுது
    -0.06
     Both
    -0.06
     all
    -0.06
     bordo
    -0.06
    दोनों
    -0.06
    POSITIVE LOGITS
     কিনে
    0.06
     lineal
    0.06
    Pak
    0.06
    find
    0.06
    濰
    0.06
     Scarlett
    0.06
     વિદ્ય
    0.06
    ธ
    0.06
     Mai
    0.06
     gezeigt
    0.06
    Activations Density 0.002%

    No Known Activations