© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128269
    Prev
    Next
    INDEX
    Explanations

    country or place names

    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
     هیڅ
    -0.06
    玫
    -0.06
    但他
    -0.05
    اؤ
    -0.05
     pertama
    -0.05
    nth
    -0.05
    أن
    -0.05
     våra
    -0.05
    ﺛ
    -0.05
    。“
    -0.05
    POSITIVE LOGITS
     horrible
    0.07
     touted
    0.06
     লাগবে
    0.06
     your
    0.06
    alz
    0.06
     நடந்தது
    0.06
     நடைபெறும்
    0.06
     nab
    0.06
    etzung
    0.06
     sog
    0.06
    Activations Density 0.010%

    No Known Activations