© 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. 120138
    Prev
    Next
    INDEX
    Explanations

    Build Status links

    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
     averigu
    -0.07
    本次
    -0.07
    討論
    -0.06
    Discussion
    -0.06
    本文
    -0.06
    城市的
    -0.06
     Discussion
    -0.06
     რამდენ
    -0.06
     Actually
    -0.06
     जानेंगे
    -0.06
    POSITIVE LOGITS
     by
    0.08
    =
    0.07
    सुद्धा
    0.06
    なども
    0.06
     in
    0.06
    at
    0.06
    f
    0.06
     как
    0.06
     at
    0.06
    などに
    0.06
    Activations Density 0.003%

    No Known Activations