© 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. 117329
    Prev
    Next
    INDEX
    Explanations

    quantities expressing plurality or amounts

    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
     মহিলাদের
    -0.06
     clearest
    -0.06
    พาะ
    -0.06
    。[
    -0.06
     系列
    -0.06
     abund
    -0.05
    ختار
    -0.05
    系列
    -0.05
    legal
    -0.05
    how
    -0.05
    POSITIVE LOGITS
     በጣም
    0.06
    壓縮
    0.06
     mặc
    0.06
     more
    0.06
     costas
    0.06
    高性能
    0.06
     قیم
    0.06
    ᄀ
    0.06
    らかじめ
    0.06
     సంబంధ
    0.06
    Activations Density 0.027%

    No Known Activations