© 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. 117482
    Prev
    Next
    INDEX
    Explanations

    wealth and elite people

    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
     такую
    -0.06
    虐
    -0.06
     PAV
    -0.06
     пыта
    -0.06
     coercion
    -0.06
    ッキリ
    -0.06
    ्सा
    -0.06
     Reaction
    -0.05
    psych
    -0.05
     والله
    -0.05
    POSITIVE LOGITS
    의
    0.07
     drastically
    0.06
     primary
    0.06
     একেবারেই
    0.06
     primarily
    0.06
    殳
    0.06
     personalization
    0.06
    專家
    0.06
    专家
    0.06
     সময়ের
    0.06
    Activations Density 0.006%

    No Known Activations