© 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. 118322
    Prev
    Next
    INDEX
    Explanations

    amateur

    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
     रचा
    -0.06
     put
    -0.06
    々と
    -0.06
     этот
    -0.06
     three
    -0.06
    quanto
    -0.06
     early
    -0.06
     on
    -0.06
     তিনটি
    -0.06
     dieses
    -0.05
    POSITIVE LOGITS
     কথা
    0.06
    VERSION
    0.06
     گروپ
    0.06
    Natal
    0.06
     amateur
    0.06
    🔁
    0.06
    Раз
    0.06
     nonprofit
    0.06
     versão
    0.06
     краси
    0.06
    Activations Density 0.003%

    No Known Activations