© 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. 118042
    Prev
    Next
    INDEX
    Explanations

    `Q:` and code/technical terms

    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
     seven
    -0.07
     four
    -0.07
     three
    -0.07
     négy
    -0.07
    James
    -0.07
    seven
    -0.06
     PEACE
    -0.06
     six
    -0.06
    两
    -0.06
     सात
    -0.06
    POSITIVE LOGITS
     일부
    0.06
     will
    0.06
     bet
    0.06
     retiring
    0.05
     covering
    0.05
    ката
    0.05
     पांव
    0.05
     rivets
    0.05
    Mit
    0.05
     visually
    0.05
    Activations Density 0.001%

    No Known Activations