© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118959
    Prev
    Next
    INDEX
    Explanations

    repair and service dates

    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
     burdensome
    -0.07
     beaucoup
    -0.06
     Beaucoup
    -0.06
     Peachtree
    -0.06
     Bien
    -0.06
     perhaps
    -0.06
     decade
    -0.06
     defens
    -0.06
     בשנת
    -0.06
    लान
    -0.06
    POSITIVE LOGITS
    日
    0.07
     сегодня
    0.07
     overcame
    0.06
     antib
    0.06
     necessários
    0.06
    days
    0.06
     dnev
    0.06
     yesterday
    0.06
    今日も
    0.06
     days
    0.06
    Activations Density 0.042%

    No Known Activations