© 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. 117475
    Prev
    Next
    INDEX
    Explanations

    Veterans Memorial, Zimbabwe swears, Distribution of

    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
    👶
    -0.07
    检查
    -0.07
     itinerary
    -0.07
    檢查
    -0.06
    每
    -0.06
     tiap
    -0.06
     प्रवाह
    -0.06
    udere
    -0.06
     each
    -0.06
    ogni
    -0.06
    POSITIVE LOGITS
     fashionable
    0.06
    !!!!!!
    0.06
     Parish
    0.06
                              
    0.06
    !!
    0.06
     gulp
    0.06
     gain
    0.06
    !!!
    0.05
     stupid
    0.05
    企
    0.05
    Activations Density 0.002%

    No Known Activations