© 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. 116838
    Prev
    Next
    INDEX
    Explanations

    questions starting with "is this" or "does"

    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
    我们的
    -0.08
    我們
    -0.07
     Bunun
    -0.07
     our
    -0.07
    我們的
    -0.07
     vår
    -0.07
     unserem
    -0.07
     nostra
    -0.07
     нашем
    -0.06
    私たちの
    -0.06
    POSITIVE LOGITS
    各
    0.06
     (
    0.06
     दोनों
    0.06
     মরদেহ
    0.06
     tantos
    0.06
     John
    0.05
     Các
    0.05
     UM
    0.05
     Bản
    0.05
    пански
    0.05
    Activations Density 0.018%

    No Known Activations