© 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. 119332
    Prev
    Next
    INDEX
    Explanations

    government agencies

    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
     হিসেবে
    -0.06
    ifford
    -0.06
     Administrators
    -0.06
     administrators
    -0.06
     ಇರುವ
    -0.06
    enment
    -0.06
     Additional
    -0.06
    ாக
    -0.05
     rifles
    -0.05
     croy
    -0.05
    POSITIVE LOGITS
    动力
    0.06
     dient
    0.06
    Semi
    0.06
    Sous
    0.06
     constitu
    0.06
     havde
    0.06
     impactos
    0.06
    投げ
    0.06
     사용하여
    0.06
     dicha
    0.06
    Activations Density 0.001%

    No Known Activations