© 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. 120246
    Prev
    Next
    INDEX
    Explanations

    ladies and gentlemen, second

    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
     développement
    -0.07
    的小
    -0.06
     pone
    -0.06
    了好
    -0.06
    将
    -0.06
    ONLY
    -0.06
    หน้า
    -0.06
    的是
    -0.06
    をし
    -0.06
    全
    -0.06
    POSITIVE LOGITS
     দৈত্য
    0.06
     उपाय
    0.06
     but
    0.06
    reports
    0.06
    umlu
    0.06
    report
    0.06
     analiz
    0.06
    )})$
    0.05
     এই
    0.05
    amazing
    0.05
    Activations Density 0.001%

    No Known Activations