© 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. 129578
    Prev
    Next
    INDEX
    Explanations

    controller in code

    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
    活力
    -0.06
     առաջ
    -0.06
     требу
    -0.06
     Wellbeing
    -0.06
     livet
    -0.06
    ന്നെ
    -0.06
    寻求
    -0.06
     Leading
    -0.06
    olive
    -0.06
     എത്ത
    -0.06
    POSITIVE LOGITS
     最后
    0.06
    逶
    0.06
     wire
    0.06
    最终
    0.06
    最后
    0.06
     dakika
    0.06
    BBC
    0.06
     rotation
    0.06
    段階
    0.06
    youtube
    0.06
    Activations Density 0.003%

    No Known Activations