© 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. 129586
    Prev
    Next
    INDEX
    Explanations

    testing and code coverage

    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
    particularly
    -0.07
    오늘은
    -0.06
    CCIÓN
    -0.06
     Expanding
    -0.06
     Getting
    -0.06
     expansive
    -0.06
    ™
    -0.06
     संक्रमण
    -0.06
     conjunction
    -0.06
    producto
    -0.06
    POSITIVE LOGITS
     уже
    0.06
     already
    0.06
    允許
    0.06
    已
    0.06
    允许
    0.06
    already
    0.06
     допуска
    0.05
    2
    0.05
    Only
    0.05
     juba
    0.05
    Activations Density 0.001%

    No Known Activations