© 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. 116764
    Prev
    Next
    INDEX
    Explanations

    was followed by measurements

    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
     because
    -0.07
     Because
    -0.06
     Additionally
    -0.06
     However
    -0.06
     BECAUSE
    -0.06
     Referred
    -0.06
     Tuttavia
    -0.06
    也就是说
    -0.06
    skull
    -0.06
     Потому
    -0.06
    POSITIVE LOGITS
    olojik
    0.07
    -​
    0.06
     সকল
    0.06
     repetitive
    0.06
    ངས་
    0.06
     včetně
    0.06
    となります
    0.05
     ทุก
    0.05
     your
    0.05
    period
    0.05
    Activations Density 0.016%

    No Known Activations