© 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. 128967
    Prev
    Next
    INDEX
    Explanations

    alert;Q:

    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
     albeit
    -0.07
     serta
    -0.07
    albeit
    -0.06
     असफल
    -0.06
    但他
    -0.06
     unsuccessful
    -0.06
     sowie
    -0.06
     despite
    -0.06
     mitad
    -0.06
     believes
    -0.06
    POSITIVE LOGITS
     combining
    0.07
     Combining
    0.07
     вызвать
    0.06
    urrent
    0.06
     modernize
    0.06
    🍉
    0.06
    getCurrent
    0.06
    temporary
    0.06
    Combining
    0.06
     chaining
    0.06
    Activations Density 0.001%

    No Known Activations