© 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. 118418
    Prev
    Next
    INDEX
    Explanations

    parent-of-origin effects

    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
     Constantinople
    -0.07
    に対
    -0.07
    频繁
    -0.06
    专注
    -0.06
     해도
    -0.06
    頻
    -0.06
    籲
    -0.06
    rej
    -0.06
     poodle
    -0.06
     細
    -0.06
    POSITIVE LOGITS
     correctly
    0.06
     nursery
    0.06
     দ্বিতীয়
    0.06
     અલગ
    0.06
     timer
    0.06
     orphan
    0.06
     karış
    0.06
     opposite
    0.06
     Timer
    0.05
     delegated
    0.05
    Activations Density 0.005%

    No Known Activations