© 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. 117334
    Prev
    Next
    INDEX
    Explanations

    to have it

    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
     所以
    -0.07
     实
    -0.07
     harrowing
    -0.07
    っちゃ
    -0.06
    所以
    -0.06
    iação
    -0.06
     তাহারা
    -0.06
     aktuell
    -0.06
    ͉
    -0.06
    菈
    -0.06
    POSITIVE LOGITS
     such
    0.06
    সহ
    0.06
     provide
    0.06
    काइ
    0.05
     प्रिया
    0.05
     наличи
    0.05
    लट
    0.05
     тако
    0.05
    acons
    0.05
     mj
    0.05
    Activations Density 0.024%

    No Known Activations