© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 131064
    Prev
    Next
    INDEX
    Explanations

    people receiving aid or shelter

    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
     নানান
    -0.06
    之間的
    -0.06
     posizione
    -0.06
    円以上
    -0.06
    因此
    -0.06
    特に
    -0.06
     माहिती
    -0.06
    pkins
    -0.06
     Ideen
    -0.06
     özellikle
    -0.06
    POSITIVE LOGITS
     bestow
    0.06
     individually
    0.06
     vivienda
    0.06
     इन्हें
    0.06
    安置
    0.06
     selected
    0.06
     sitcom
    0.06
     இருக்கு
    0.06
    cluding
    0.06
     kehidupan
    0.06
    Activations Density 0.048%

    No Known Activations