© 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. 129623
    Prev
    Next
    INDEX
    Explanations

    possession or association

    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
     impec
    -0.06
     প্রত্যা
    -0.06
     दोघा
    -0.06
    params
    -0.06
     weiterhin
    -0.06
     부탁
    -0.06
     sporad
    -0.05
    potion
    -0.05
    privileged
    -0.05
     privileged
    -0.05
    POSITIVE LOGITS
    }=(-
    0.07
     correspondiente
    0.07
    顯示
    0.07
    就有
    0.07
    Essential
    0.07
     Essential
    0.07
    日本
    0.06
     সহজেই
    0.06
    的重要
    0.06
    あるいは
    0.06
    Activations Density 0.002%

    No Known Activations